File size: 85,760 Bytes
a0b2878 a5ed10e a0b2878 672fbe5 ed428df a0b2878 bc09f18 0cabd57 bc09f18 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 6ada8bb a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 e79b4fa a0b2878 96d222e a0b2878 e861f2a a0b2878 55756c1 a0b2878 e861f2a ab2d5c7 e861f2a 1127598 e861f2a a0b2878 6ada8bb a0b2878 af10e85 b920bff 076ae22 af10e85 a0b2878 af10e85 b920bff 076ae22 af10e85 a0b2878 e861f2a bdef4c2 e861f2a a0b2878 ab2d5c7 a0b2878 2db3a13 a0b2878 2db3a13 a0b2878 5b565c5 a0b2878 55ab13c a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 55ab13c a0b2878 55ab13c a0b2878 ab2d5c7 a0b2878 ab2d5c7 d921074 ff38376 d921074 ff38376 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 55ab13c d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 9f3a6e2 a0b2878 d921074 a0b2878 d921074 eeb25c9 d921074 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 eeb25c9 d921074 a0b2878 ab2d5c7 a0b2878 d921074 a0b2878 d921074 a0b2878 d921074 ab2d5c7 d921074 a0b2878 d921074 a0b2878 ab2d5c7 a0b2878 55ab13c a0b2878 ab2d5c7 a0b2878 55ab13c a0b2878 ab2d5c7 a0b2878 55ab13c a0b2878 ab2d5c7 a0b2878 ab2d5c7 e23c048 a0b2878 e23c048 a0b2878 e23c048 f4c0a9a e23c048 a0b2878 e23c048 f4c0a9a e23c048 f4c0a9a e23c048 f4c0a9a a0b2878 e23c048 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 ab2d5c7 a0b2878 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 | ---
license: apache-2.0
pipeline_tag: any-to-any
library_name: transformers
tags:
- minicpm-o
- minicpm-v
- multimodal
- full-duplex
---
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone
[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [CookBook](https://github.com/OpenSQZ/MiniCPM-V-CookBook) | [**Omni-modal Demo**](https://35.226.63.1:8008/) | [Vision-Language Demo](http://211.93.21.133:18121/) </br>
[WeChat](https://github.com/OpenBMB/MiniCPM-o/blob/main/docs/wechat.md) | [Discord](https://discord.gg/N2RnxGdJ) | [Audio Casebook](https://openbmb.github.io/minicpm-o-4_5/) </a> | [Omni Full-Duplex Casebook](https://openbmb.github.io/minicpm-o-4_5-omni/)
## News
> [!NOTE]
> [2026.02.06] 🥳 🥳 🥳 We open-sourced a realtime web demo deployable on your own devices like Mac or GPU. [Try it now](#deploy-a-realtime-web-demo-on-your-own-device)!
## MiniCPM-o 4.5
**MiniCPM-o 4.5** is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include:
- 🔥 **Leading Visual Capability.**
MiniCPM-o 4.5 achieves an average score of 77.6 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. **With only 9B parameters, it surpasses widely used proprietary models like GPT-4o, Gemini 2.0 Pro, and approaches Gemini 2.5 Flash** for vision-language capabilities. It supports instruct and thinking modes in a single model, better covering efficiency and performance trade-offs in different user scenarios.
- 🎙 **Strong Speech Capability.**
MiniCPM-o 4.5 supports **bilingual real-time speech conversation with configurable voices** in English and Chinese. It features **more natural, expressive and stable speech conversation**. The model also allows for fun features such as **voice cloning and role play via a simple reference audio clip**, where the cloning performance surpasses strong TTS tools such as CosyVoice2.
- 🎬 **New Full-Duplex and Proactive Multimodal Live Streaming Capability.**
As a new feature, MiniCPM-o 4.5 can process real-time, continuous video and audio input streams simultaneously while generating concurrent text and speech output streams in an end-to-end fashion, without mutual blocking. This **allows MiniCPM-o 4.5 to see, listen, and speak simultaneously**, creating a fluid, real-time omnimodal conversation experience. Beyond reactive responses, the model can also perform **proactive interaction**, such as initiating reminders or comments based on its continuous understanding of the live scene.
- 💪 **Strong OCR Capability, Efficiency and Others.**
Advancing popular visual capabilities from MiniCPM-V series, MiniCPM-o 4.5 can process **high-resolution images** (up to 1.8 million pixels) and **high-FPS videos** (up to 10fps) in any aspect ratio efficiently. It achieves **state-of-the-art performance for end-to-end English document parsing** on OmniDocBench, outperforming proprietary models such as Gemini-3 Flash and GPT-5, and specialized tools such as DeepSeek-OCR 2. It also features **trustworthy behaviors**, matching Gemini 2.5 Flash on MMHal-Bench, and supports **multilingual capabilities** on more than 30 languages.
- 💫 **Easy Usage.**
MiniCPM-o 4.5 can be easily used in various ways: **Basic usage, recommended for 100% precision:** PyTorch inference with Nvidia GPU. **Other end-side adaptation** includes (1) llama.cpp and Ollama support for efficient CPU inference on local devices, (2) int4 and GGUF format quantized models in 16 sizes, (3) vLLM and SGLang support for high-throughput and memory-efficient inference, (4) FlagOS support for the unified multi-chip backend plugin. **We also open-sourced web demos** on which **enables the full-duplex multimodal live streaming experience on local devices** such as GPUs, PCs (e.g., on a MacBook).
**Model Architecture.**
- **End-to-end Omni-modal Architecture.** The modality encoders/decoders and LLM are densely connected via hidden states in an end-to-end fashion. This enables better information flow and control, and also facilitates full exploitation of rich multimodal knowledge during training.
- **Full-Duplex Omni-modal Live Streaming Mechanism.** (1) We turn the offline modality encoder/decoders into online and full-duplex ones for streaming inputs/outputs. The speech token decoder models text and speech tokens in an interleaved fashion to support full-duplex speech generation (i.e., sync timely with new input). This also facilitates more stable long speech generation (e.g., > 1min).
(2) **We sync all the input and output streams on timeline in milliseconds**, which are jointly modeled by a time-division multiplexing (TDM) mechanism for omni-modality streaming processing in the LLM backbone. It divides parallel omni-modality streams into sequential info groups within small periodic time slices.
- **Proactive Interaction Mechanism.** The LLM continuously monitors the input video and audio streams, and decides at a frequency of 1Hz to speak or not. This high decision-making frequency together with full-duplex nature are curcial to enable the proactive interaction capability.
- **Configurable Speech Modeling Design.** We inherent the multimodal system prompt design of MiniCPM-o 2.6, which includes a traditional text system prompt, and a new audio system prompt to determine the assistant voice. This enables cloning new voices and role play in inference time for speech conversation.
<div align="center">
<img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpm-o-45-framework.png" width=100%>
</div>
### Evaluation <!-- omit in toc -->
<div align="center">
<img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/radar_minicpmo4.5.png", width=80%>
</div>
<div align="center">
<img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpm_o_45_main_exp_table.png", width=90%>
</div>
<strong>Note</strong>: Scores marked with ∗ are from our evaluation; others are cited from referenced reports. n/a indicates that the model does not support the corresponding modality. All results are reported in instruct mode/variant.
 
<br>
<details>
<summary>Click to view visual understanding results.</summary>
**Image Understanding (Instruct)**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>OpenCompass</b></th>
<th nowrap="nowrap"><b>MMBench EN v1.1</b></th>
<th nowrap="nowrap"><b>MMBench CN v1.1</b></th>
<th nowrap="nowrap"><b>MathVista</b></th>
<th nowrap="nowrap"><b>MMVet</b></th>
<th nowrap="nowrap"><b>MMMU</b></th>
<th nowrap="nowrap"><b>MMStar</b></th>
<th nowrap="nowrap"><b>HallusionBench</b></th>
<th nowrap="nowrap"><b>AI2D</b></th>
<th nowrap="nowrap"><b>OCRBench</b></th>
<th nowrap="nowrap"><b>TextVQA_VAL</b></th>
<th nowrap="nowrap"><b>DocVQA_VAL</b></th>
<th nowrap="nowrap"><b>MMT-Bench_VAL</b></th>
<th nowrap="nowrap"><b>MM-IFEval</b></th>
<th nowrap="nowrap"><b>Mantis-Eval</b></th>
<th nowrap="nowrap"><b>MuirBench</b></th>
<th nowrap="nowrap"><b>MMSI-Bench</b></th>
<th nowrap="nowrap"><b>MMHal-Score</b></th>
<th nowrap="nowrap"><b>MMHal-Hallrate↓</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Gemini2.5-Flash-Nonthinking</td>
<td align="center"><b>78.5</b></td>
<td align="center"><ins>86.6</ins></td>
<td align="center"><ins>86.0</ins></td>
<td align="center">75.3</td>
<td align="center"><ins>81.4</ins><sup>*</sup></td>
<td align="center"><b>76.3</b></td>
<td align="center"><b>75.8</b></td>
<td align="center">59.1</td>
<td align="center"><b>87.7</b></td>
<td align="center">864</td>
<td align="center">74.3<sup>*</sup></td>
<td align="center">93.0</td>
<td align="center"><ins>70.0</ins><sup>*</sup></td>
<td align="center"><b>75.8<sup>*</sup></b></td>
<td align="center">72.8<sup>*</sup></td>
<td align="center"><b>74.5<sup>*</sup></b></td>
<td align="center">12.1<sup>*</sup></td>
<td align="center"><ins>4.6</ins><sup>*</sup></td>
<td align="center"><b>23.9<sup>*</sup></b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Gemini2.0-Pro</td>
<td align="center">73.3</td>
<td align="center">83.0</td>
<td align="center">83.0</td>
<td align="center">71.3</td>
<td align="center">70.4</td>
<td align="center">72.6</td>
<td align="center">68.5</td>
<td align="center">49.8</td>
<td align="center">84.8</td>
<td align="center">863</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
<td align="center">-</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">GPT-4o</td>
<td align="center">75.4</td>
<td align="center">86.0</td>
<td align="center"><ins>86.0</ins></td>
<td align="center">71.6</td>
<td align="center">76.9</td>
<td align="center">72.9</td>
<td align="center">70.2</td>
<td align="center">57.0</td>
<td align="center">86.3</td>
<td align="center">822</td>
<td align="center">77.4</td>
<td align="center">93.0</td>
<td align="center">66.7<sup>*</sup></td>
<td align="center">64.6</td>
<td align="center">70.1<sup>*</sup></td>
<td align="center">70.5<sup>*</sup></td>
<td align="center">8.1<sup>*</sup></td>
<td align="center">4.2<sup>*</sup></td>
<td align="center">25.0<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">InternVL-3.5-8B</td>
<td align="center">75.8</td>
<td align="center">79.5</td>
<td align="center">80.0<sup>*</sup></td>
<td align="center"><ins>78.4</ins></td>
<td align="center"><b>83.1</b></td>
<td align="center"><ins>73.4</ins></td>
<td align="center">69.3</td>
<td align="center">54.5</td>
<td align="center">84.0</td>
<td align="center">840</td>
<td align="center">78.2</td>
<td align="center">92.3</td>
<td align="center">66.7</td>
<td align="center">56.3<sup>*</sup></td>
<td align="center">70.5</td>
<td align="center">55.8</td>
<td align="center">-</td>
<td align="center">3.8<sup>*</sup></td>
<td align="center">34.7<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-VL-8B-Instruct</td>
<td align="center">76.5</td>
<td align="center">84.5</td>
<td align="center">84.7</td>
<td align="center">77.2</td>
<td align="center">73.7<sup>*</sup></td>
<td align="center">69.6</td>
<td align="center">70.9</td>
<td align="center"><ins>61.1</ins></td>
<td align="center">85.7</td>
<td align="center"><b>896</b></td>
<td align="center">82.9<sup>*</sup></td>
<td align="center"><b>96.1</b></td>
<td align="center">60.9<sup>*</sup></td>
<td align="center">59.4<sup>*</sup></td>
<td align="center">74.2<sup>*</sup></td>
<td align="center">64.4</td>
<td align="center">11.3<sup>*</sup></td>
<td align="center"><b>4.7<sup>*</sup></b></td>
<td align="center">29.9<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center">75.7</td>
<td align="center">84.9<sup>*</sup></td>
<td align="center">84.1<sup>*</sup></td>
<td align="center">75.9</td>
<td align="center">74.8<sup>*</sup></td>
<td align="center">69.1</td>
<td align="center">68.5</td>
<td align="center">59.7</td>
<td align="center">85.2</td>
<td align="center"><ins>880</ins><sup>*</sup></td>
<td align="center"><b>84.1<sup>*</sup></b></td>
<td align="center"><ins>95.4</ins><sup>*</sup></td>
<td align="center"><b>70.4<sup>*</sup></b></td>
<td align="center">65.7<sup>*</sup></td>
<td align="center"><ins>78.3</ins><sup>*</sup></td>
<td align="center">61.9<sup>*</sup></td>
<td align="center"><ins>14.2</ins><sup>*</sup></td>
<td align="center"><ins>4.6</ins><sup>*</sup></td>
<td align="center">31.6<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><ins>77.6</ins></td>
<td align="center"><b>87.6</b></td>
<td align="center"><b>87.2</b></td>
<td align="center"><b>80.1</b></td>
<td align="center">74.4</td>
<td align="center">67.6</td>
<td align="center"><ins>73.1</ins></td>
<td align="center"><b>63.2</b></td>
<td align="center"><ins>87.6</ins></td>
<td align="center">876</td>
<td align="center"><ins>83.8</ins></td>
<td align="center">94.7</td>
<td align="center">69.7</td>
<td align="center"><ins>66.3</ins></td>
<td align="center"><b>79.7</b></td>
<td align="center"><ins>72.0</ins></td>
<td align="center"><b>16.6</b></td>
<td align="center"><b>4.7</b></td>
<td align="center"><ins>24.3</ins></td>
</tr>
</table>
</div>
**Image Understanding (Thinking)**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>OpenCompass</b></th>
<th nowrap="nowrap"><b>MMBench EN v1.1</b></th>
<th nowrap="nowrap"><b>MMBench CN v1.1</b></th>
<th nowrap="nowrap"><b>MathVista</b></th>
<th nowrap="nowrap"><b>MMVet</b></th>
<th nowrap="nowrap"><b>MMMU</b></th>
<th nowrap="nowrap"><b>MMStar</b></th>
<th nowrap="nowrap"><b>HallusionBench</b></th>
<th nowrap="nowrap"><b>AI2D</b></th>
<th nowrap="nowrap"><b>OCRBench</b></th>
<th nowrap="nowrap"><b>TextVQA_VAL</b></th>
<th nowrap="nowrap"><b>DocVQA_VAL</b></th>
<th nowrap="nowrap"><b>MMT-Bench_VAL</b></th>
<th nowrap="nowrap"><b>MM-IFEval</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Gemini2.5-Flash-Thinking</td>
<td align="center"><b>79.9</b></td>
<td align="center">87.1</td>
<td align="center">87.3</td>
<td align="center">79.4</td>
<td align="center"><b>81.2<sup>*</sup></b></td>
<td align="center"><ins>77.7</ins></td>
<td align="center"><b>76.5</b></td>
<td align="center">63.5</td>
<td align="center"><ins>88.7</ins></td>
<td align="center">853</td>
<td align="center">73.8<sup>*</sup></td>
<td align="center">92.8</td>
<td align="center">70.7<sup>*</sup></td>
<td align="center"><ins>75.7</ins><sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">GPT-5</td>
<td align="center"><ins>79.7</ins></td>
<td align="center">85.5<sup>*</sup></td>
<td align="center">85.6<sup>*</sup></td>
<td align="center"><b>81.9</b></td>
<td align="center"><ins>77.6</ins></td>
<td align="center"><b>81.8</b></td>
<td align="center"><ins>75.7</ins></td>
<td align="center"><ins>65.2</ins></td>
<td align="center"><b>89.5</b></td>
<td align="center">807</td>
<td align="center">77.8<sup>*</sup></td>
<td align="center">91.3<sup>*</sup></td>
<td align="center"><b>72.7<sup>*</sup></b></td>
<td align="center"><b>83.1<sup>*</sup></b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-VL-8B-Thinking</td>
<td align="center">77.3</td>
<td align="center">85.3</td>
<td align="center">85.5</td>
<td align="center"><ins>81.4</ins></td>
<td align="center">69.8<sup>*</sup></td>
<td align="center">74.1</td>
<td align="center">75.3</td>
<td align="center"><b>65.4</b></td>
<td align="center">84.9</td>
<td align="center">819</td>
<td align="center">77.8<sup>*</sup></td>
<td align="center"><b>95.3</b></td>
<td align="center">68.1<sup>*</sup></td>
<td align="center">73.5<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Thinking</td>
<td align="center">78.5</td>
<td align="center"><ins>88.2</ins><sup>*</sup></td>
<td align="center"><b>87.7<sup>*</sup></b></td>
<td align="center">80.0</td>
<td align="center">74.8<sup>*</sup></td>
<td align="center">75.6</td>
<td align="center">74.9</td>
<td align="center">62.8</td>
<td align="center">86.1</td>
<td align="center"><ins>859</ins><sup>*</sup></td>
<td align="center"><b>80.8<sup>*</sup></b></td>
<td align="center"><ins>94.2</ins><sup>*</sup></td>
<td align="center"><ins>70.9</ins><sup>*</sup></td>
<td align="center">69.9<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Thinking</td>
<td align="center">78.2</td>
<td align="center"><b>89.0</b></td>
<td align="center"><ins>87.6</ins></td>
<td align="center">81.0</td>
<td align="center">73.6</td>
<td align="center">70.2</td>
<td align="center">73.6</td>
<td align="center">62.6</td>
<td align="center">88.5</td>
<td align="center"><b>879</b></td>
<td align="center"><ins>79.8</ins></td>
<td align="center">92.3</td>
<td align="center">69.7</td>
<td align="center">68.2</td>
</tr>
</table>
</div>
**Video Understanding**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>Video-MME<br>(w/o subs)</b></th>
<th nowrap="nowrap"><b>LVBench</b></th>
<th nowrap="nowrap"><b>MLVU<br>(M-Avg)</b></th>
<th nowrap="nowrap"><b>LongVideoBench<br>(val)</b></th>
<th nowrap="nowrap"><b>MotionBench</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Gemini2.5-Flash-Nonthinking</td>
<td align="center"><b>75.6</b></td>
<td align="center"><b>62.2</b></td>
<td align="center"><b>77.8</b></td>
<td align="center">-</td>
<td align="center">-</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">InternVL-3.5-8B</td>
<td align="center">66.0</td>
<td align="center">-</td>
<td align="center">70.2</td>
<td align="center">62.1</td>
<td align="center"><b>62.3<sup>*</sup></b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center"><ins>70.5</ins></td>
<td align="center">50.2</td>
<td align="center">75.2</td>
<td align="center"><b>66.9<sup>*</sup></b></td>
<td align="center"><ins>61.7</ins><sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center">70.4</td>
<td align="center"><ins>50.9</ins></td>
<td align="center"><ins>76.5</ins></td>
<td align="center"><ins>66.0</ins></td>
<td align="center">61.4</td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view document parsing results.</summary>
**OmniDocBench**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left" rowspan="2"><b>Method Type</b></th>
<th nowrap="nowrap" rowspan="2"><b>Methods</b></th>
<th nowrap="nowrap" colspan="2"><b>OverallEdit↓</b></th>
<th nowrap="nowrap" colspan="2"><b>TextEdit↓</b></th>
<th nowrap="nowrap" colspan="2"><b>FormulaEdit↓</b></th>
<th nowrap="nowrap" colspan="2"><b>TableTEDS↑</b></th>
<th nowrap="nowrap" colspan="2"><b>TableEdit↓</b></th>
<th nowrap="nowrap" colspan="2"><b>Read OrderEdit↓</b></th>
</tr>
<tr>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
<th nowrap="nowrap"><b>EN</b></th>
<th nowrap="nowrap"><b>ZH</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left" rowspan="2">Pipeline</td>
<td nowrap="nowrap" align="center">MinerU 2.5</td>
<td align="center">0.117<sup>*</sup></td>
<td align="center">0.172<sup>*</sup></td>
<td align="center">0.051<sup>*</sup></td>
<td align="center">0.08<sup>*</sup></td>
<td align="center"><ins>0.256</ins><sup>*</sup></td>
<td align="center">0.455<sup>*</sup></td>
<td align="center">85.9<sup>*</sup></td>
<td align="center">89.4<sup>*</sup></td>
<td align="center">0.115<sup>*</sup></td>
<td align="center">0.081<sup>*</sup></td>
<td align="center">0.047<sup>*</sup></td>
<td align="center">0.072<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">PaddleOCR-VL</td>
<td align="center"><b>0.105</b></td>
<td align="center"><ins>0.126</ins></td>
<td align="center"><ins>0.041</ins></td>
<td align="center"><b>0.062</b></td>
<td align="center"><b>0.241</b></td>
<td align="center"><b>0.316</b></td>
<td align="center">88</td>
<td align="center"><ins>92.1</ins></td>
<td align="center"><ins>0.093</ins></td>
<td align="center"><ins>0.062</ins></td>
<td align="center">0.045</td>
<td align="center"><ins>0.063</ins></td>
</tr>
<tr>
<td nowrap="nowrap" align="left"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
<td align="center"></td>
</tr>
<tr>
<td nowrap="nowrap" align="left" rowspan="11">End-to-end Model</td>
<td nowrap="nowrap" align="center">Qwen2.5-VL-72B</td>
<td align="center">0.214</td>
<td align="center">0.261</td>
<td align="center">0.092</td>
<td align="center">0.18</td>
<td align="center">0.315</td>
<td align="center">0.434</td>
<td align="center">82.9</td>
<td align="center">83.9</td>
<td align="center">0.341</td>
<td align="center">0.262</td>
<td align="center">0.106</td>
<td align="center">0.168</td>
</tr>
<tr>
<td nowrap="nowrap" align="center">GPT 5</td>
<td align="center">0.218<sup>*</sup></td>
<td align="center">0.33<sup>*</sup></td>
<td align="center">0.139<sup>*</sup></td>
<td align="center">0.344<sup>*</sup></td>
<td align="center">0.396<sup>*</sup></td>
<td align="center">0.555<sup>*</sup></td>
<td align="center">77.55<sup>*</sup></td>
<td align="center">73.09<sup>*</sup></td>
<td align="center">0.188<sup>*</sup></td>
<td align="center">0.196<sup>*</sup></td>
<td align="center">0.151<sup>*</sup></td>
<td align="center">0.227<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">Gemini2.5-Flash-Nonthinking</td>
<td align="center">0.214<sup>*</sup></td>
<td align="center">0.29<sup>*</sup></td>
<td align="center">0.159<sup>*</sup></td>
<td align="center">0.273<sup>*</sup></td>
<td align="center">0.368<sup>*</sup></td>
<td align="center">0.524<sup>*</sup></td>
<td align="center">80.9<sup>*</sup></td>
<td align="center">85.5<sup>*</sup></td>
<td align="center">0.197<sup>*</sup></td>
<td align="center">0.167<sup>*</sup></td>
<td align="center">0.132<sup>*</sup></td>
<td align="center">0.195<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">Gemini-2.5-Pro-Nonthinking</td>
<td align="center">0.148<sup>*</sup></td>
<td align="center">0.212<sup>*</sup></td>
<td align="center">0.055<sup>*</sup></td>
<td align="center">0.168<sup>*</sup></td>
<td align="center">0.356<sup>*</sup></td>
<td align="center">0.439<sup>*</sup></td>
<td align="center">85.8<sup>*</sup></td>
<td align="center">86.4<sup>*</sup></td>
<td align="center">0.13<sup>*</sup></td>
<td align="center">0.119<sup>*</sup></td>
<td align="center">0.049<sup>*</sup></td>
<td align="center">0.121<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">Gemini-3 Flash-Nonthinking</td>
<td align="center">0.155<sup>*</sup></td>
<td align="center">0.201<sup>*</sup></td>
<td align="center">0.138<sup>*</sup></td>
<td align="center">0.255<sup>*</sup></td>
<td align="center">0.297<sup>*</sup></td>
<td align="center">0.351<sup>*</sup></td>
<td align="center">86.4<sup>*</sup></td>
<td align="center">89.8<sup>*</sup></td>
<td align="center">0.116<sup>*</sup></td>
<td align="center">0.1<sup>*</sup></td>
<td align="center">0.072<sup>*</sup></td>
<td align="center">0.099<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">doubao-1-5-thinking-vision-pro-250428</td>
<td align="center">0.14</td>
<td align="center">0.162</td>
<td align="center">0.043</td>
<td align="center">0.085</td>
<td align="center">0.295</td>
<td align="center">0.384</td>
<td align="center">83.3</td>
<td align="center">89.3</td>
<td align="center">0.165</td>
<td align="center">0.085</td>
<td align="center">0.058</td>
<td align="center">0.094</td>
</tr>
<tr>
<td nowrap="nowrap" align="center">dots.ocr</td>
<td align="center">0.125</td>
<td align="center">0.16</td>
<td align="center"><b>0.032</b></td>
<td align="center"><ins>0.066</ins></td>
<td align="center">0.329</td>
<td align="center">0.416</td>
<td align="center"><ins>88.6</ins></td>
<td align="center">89</td>
<td align="center">0.099</td>
<td align="center">0.092</td>
<td align="center"><ins>0.04</ins></td>
<td align="center">0.067</td>
</tr>
<tr>
<td nowrap="nowrap" align="center">HunyuanOCR</td>
<td align="center">0.12<sup>*</sup></td>
<td align="center"><b>0.125<sup>*</sup></b></td>
<td align="center">0.046<sup>*</sup></td>
<td align="center">0.071<sup>*</sup></td>
<td align="center">0.288<sup>*</sup></td>
<td align="center"><ins>0.33</ins><sup>*</sup></td>
<td align="center"><b>89.6<sup>*</sup></b></td>
<td align="center"><b>94.4<sup>*</sup></b></td>
<td align="center"><b>0.089<sup>*</sup></b></td>
<td align="center"><b>0.045<sup>*</sup></b></td>
<td align="center">0.055<sup>*</sup></td>
<td align="center"><b>0.056<sup>*</sup></b></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">DeepSeek-OCR 2</td>
<td align="center">0.119<sup>*</sup></td>
<td align="center">0.146<sup>*</sup></td>
<td align="center"><ins>0.041</ins><sup>*</sup></td>
<td align="center">0.08<sup>*</sup></td>
<td align="center"><ins>0.256</ins><sup>*</sup></td>
<td align="center">0.345<sup>*</sup></td>
<td align="center">82.6<sup>*</sup></td>
<td align="center">89.9<sup>*</sup></td>
<td align="center">0.123<sup>*</sup></td>
<td align="center">0.078<sup>*</sup></td>
<td align="center">0.055<sup>*</sup></td>
<td align="center">0.081<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center">0.216<sup>*</sup></td>
<td align="center">0.363<sup>*</sup></td>
<td align="center">0.128<sup>*</sup></td>
<td align="center">0.337<sup>*</sup></td>
<td align="center">0.402<sup>*</sup></td>
<td align="center">0.529<sup>*</sup></td>
<td align="center">77.3<sup>*</sup></td>
<td align="center">71.8<sup>*</sup></td>
<td align="center">0.181<sup>*</sup></td>
<td align="center">0.255<sup>*</sup></td>
<td align="center">0.152<sup>*</sup></td>
<td align="center">0.332<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="center">MiniCPM-o 4.5-Instruct</td>
<td align="center"><ins>0.109</ins></td>
<td align="center">0.162</td>
<td align="center">0.046</td>
<td align="center">0.078</td>
<td align="center">0.257</td>
<td align="center">0.41</td>
<td align="center">86.8</td>
<td align="center">88.9</td>
<td align="center">0.097</td>
<td align="center">0.084</td>
<td align="center"><b>0.037</b></td>
<td align="center">0.074</td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view text capability results.</summary>
**Text Capability**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>IFEval-PLS</b></th>
<th nowrap="nowrap"><b>BBH</b></th>
<th nowrap="nowrap"><b>CMMLU</b></th>
<th nowrap="nowrap"><b>MMLU</b></th>
<th nowrap="nowrap"><b>HumanEval</b></th>
<th nowrap="nowrap"><b>MBPP</b></th>
<th nowrap="nowrap"><b>Math500</b></th>
<th nowrap="nowrap"><b>GSM8K</b></th>
<th nowrap="nowrap"><b>Avg</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-8B-Instruct</td>
<td align="center">83.0<sup>*</sup></td>
<td align="center">69.4<sup>*</sup></td>
<td align="center">78.7<sup>*</sup></td>
<td align="center"><b>81.7<sup>*</sup></b></td>
<td align="center"><b>86.6<sup>*</sup></b></td>
<td align="center">75.9<sup>*</sup></td>
<td align="center"><b>84.0<sup>*</sup></b></td>
<td align="center">93.4<sup>*</sup></td>
<td align="center">81.6</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b>84.7</b></td>
<td align="center"><b>81.1</b></td>
<td align="center"><b>79.5</b></td>
<td align="center">77.0</td>
<td align="center"><b>86.6</b></td>
<td align="center"><b>76.7</b></td>
<td align="center">77.0</td>
<td align="center"><b>94.5</b></td>
<td align="center"><b>82.1</b></td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view omni half-duplex results.</summary>
**Omni Half-Duplex**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>Daily-Omni</b></th>
<th nowrap="nowrap"><b>WorldSense</b></th>
<th nowrap="nowrap"><b>Video-Holmes</b></th>
<th nowrap="nowrap"><b>JointAVBench</b></th>
<th nowrap="nowrap"><b>AVUT-Human</b></th>
<th nowrap="nowrap"><b>FutureOmni</b></th>
<th nowrap="nowrap"><b>Video-MME-Short<br>(w/ audio)</b></th>
<th nowrap="nowrap">Avg</th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Gemini2.5-Flash-Nonthinking</td>
<td align="center"><ins>79.3</ins><sup>*</sup></td>
<td align="center">52.6<sup>*</sup></td>
<td align="center"><ins>51.3</ins><sup>*</sup></td>
<td align="center"><ins>55.6</ins><sup>*</sup></td>
<td align="center">65.4<sup>*</sup></td>
<td align="center">55.6<sup>*</sup></td>
<td align="center"><b>85.5<sup>*</sup></b></td>
<td align="center">63.6</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center">70.7<sup>*</sup></td>
<td align="center"><ins>54.0</ins></td>
<td align="center">50.4<sup>*</sup></td>
<td align="center">53.1</td>
<td align="center"><ins>74.2</ins><sup>*</sup></td>
<td align="center"><b>62.1</b></td>
<td align="center">81.3<sup>*</sup></td>
<td align="center"><ins>63.7</ins></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b>80.2</b></td>
<td align="center"><b>55.7</b></td>
<td align="center"><b>64.3</b></td>
<td align="center"><b>60.0</b></td>
<td align="center"><b>78.6</b></td>
<td align="center"><ins>56.1</ins></td>
<td align="center"><ins>84.7</ins></td>
<td align="center"><b>68.5</b></td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view vision duplex results.</summary>
**Vision Duplex**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>LiveSports-3K-CC<br>(Win Rate vs GPT4o)</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">LiveCC-7B-Instruct</td>
<td align="center">41.5</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">StreamingVLM</td>
<td align="center"><ins>45.6</ins></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b>54.4</b></td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view audio understanding results.</summary>
**Audio Understanding**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left" rowspan="2"><b>Model</b></th>
<th nowrap="nowrap" colspan="4"><b>ASR-ZH<br>CER↓</b></th>
<th nowrap="nowrap" colspan="4"><b>ASR-EN<br>WER↓</b></th>
<th nowrap="nowrap" colspan="2"><b>AST</b></th>
<th nowrap="nowrap" colspan="2"><b>MultiTask</b></th>
<th nowrap="nowrap" colspan="4"><b>SpeechQA</b></th>
</tr>
<tr>
<th nowrap="nowrap"><b>AISHELL-1</b></th>
<th nowrap="nowrap"><b>AISHELL-2</b></th>
<th nowrap="nowrap"><b>WenetSpeech test-net</b></th>
<th nowrap="nowrap"><b>WenetSpeech test-meeting</b></th>
<th nowrap="nowrap"><b>LibriSpeech test-clean</b></th>
<th nowrap="nowrap"><b>LibriSpeech <br>test-other</b></th>
<th nowrap="nowrap"><b>GigaSpeech test</b></th>
<th nowrap="nowrap"><b>VoxPopuli-V1-En</b></th>
<th nowrap="nowrap"><b>CoVoST 2 en2zh</b></th>
<th nowrap="nowrap"><b>CoVoST 2 zh2en</b></th>
<th nowrap="nowrap"><b>MMAU</b></th>
<th nowrap="nowrap"><b>Meld</b></th>
<th nowrap="nowrap"><b>VoiceBench <br>AlpacaEval</b></th>
<th nowrap="nowrap"><b>Speech TriviaQA</b></th>
<th nowrap="nowrap"><b>Speech <br>Web Questions</b></th>
<th nowrap="nowrap"><b>Speech CMMLU</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Kimi-Audio</td>
<td align="center"><b>0.6</b></td>
<td align="center">2.6</td>
<td align="center">6.3</td>
<td align="center"><b>5.4</b></td>
<td align="center"><ins>1.3</ins></td>
<td align="center"><b>2.4</b></td>
<td align="center">9.4<sup>*</sup></td>
<td align="center">8.0<sup>*</sup></td>
<td align="center">36.6<sup>*</sup></td>
<td align="center">18.3<sup>*</sup></td>
<td align="center">68.4<sup>*</sup></td>
<td align="center"><ins>59.1</ins></td>
<td align="center">4.5</td>
<td align="center">41.9<sup>*</sup></td>
<td align="center">46.4<sup>*</sup></td>
<td align="center"><b>67.0<sup>*</sup></b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center"><b>0.6</b></td>
<td align="center"><b>2.3<sup>*</sup></b></td>
<td align="center"><b>4.7</b></td>
<td align="center">5.9</td>
<td align="center"><b>1.2</b></td>
<td align="center"><ins>2.5</ins></td>
<td align="center"><ins>8.7</ins><sup>*</sup></td>
<td align="center"><ins>6.4</ins><sup>*</sup></td>
<td align="center"><ins>46.6</ins><sup>*</sup></td>
<td align="center"><b>29.4<sup>*</sup></b></td>
<td align="center"><b>77.5</b></td>
<td align="center">56.8<sup>*</sup></td>
<td align="center"><ins>4.7</ins></td>
<td align="center"><ins>62.9</ins><sup>*</sup></td>
<td align="center"><b>74.9<sup>*</sup></b></td>
<td align="center">47.8<sup>*</sup></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><ins>0.9</ins></td>
<td align="center"><ins>2.5</ins></td>
<td align="center"><ins>5.9</ins></td>
<td align="center"><ins>5.7</ins></td>
<td align="center">1.4</td>
<td align="center">2.8</td>
<td align="center"><b>8.5</b></td>
<td align="center"><b>6.2</b></td>
<td align="center"><b>49.9</b></td>
<td align="center"><ins>26.4</ins></td>
<td align="center"><ins>76.9</ins></td>
<td align="center"><b>60.2</b></td>
<td align="center"><b>4.8</b></td>
<td align="center"><b>75.5</b></td>
<td align="center"><ins>70.2</ins></td>
<td align="center"><ins>59.2</ins></td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view speech generation results.</summary>
**Speech Generation**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>seedtts test-zh <br>CER↓</b></th>
<th nowrap="nowrap"><b>seedtts test-zh<br>SIM-o↑</b></th>
<th nowrap="nowrap"><b>seedtts test-en<br>WER↓</b></th>
<th nowrap="nowrap"><b>seedtts test-en<br>SIM-o↑</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Cosyvoice2</td>
<td align="center">1.45%</td>
<td align="center"><b>74.8</b></td>
<td align="center"><ins>2.57%</ins></td>
<td align="center"><b>65.2</b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center"><ins>1.41%</ins></td>
<td align="center">-</td>
<td align="center">3.39%</td>
<td align="center">-</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b><b>0.86%</b></b></td>
<td align="center">74.5</td>
<td align="center"><b><b>2.38%</b></b></td>
<td align="center">64.9</td>
</tr>
</table>
</div>
**Long Speech Generation**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>LongTTS-en<br>WER↓</b></th>
<th nowrap="nowrap"><b>LongTTS-zh<br>CER↓</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">CosyVoice2</td>
<td align="center"><ins>14.80%</ins></td>
<td align="center"><b>5.27%</b></td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center">17.33%</td>
<td align="center">18.99%</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b>3.37%</b></td>
<td align="center"><ins>6.58%</ins></td>
</tr>
</table>
</div>
**Emotion Control**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left"><b>Model</b></th>
<th nowrap="nowrap"><b>Expresso <br>Neutral Reference Audio↑</b></th>
<th nowrap="nowrap"><b>ESD <br>Neutral Reference Audio↑</b></th>
</tr>
<tr>
<td nowrap="nowrap" align="left">Cosyvoice2</td>
<td align="center">17.9</td>
<td align="center">53.4</td>
</tr>
<tr>
<td nowrap="nowrap" align="left">MiniCPM-o 4.5-Instruct</td>
<td align="center"><b>29.8</b></td>
<td align="center"><b>82.1</b></td>
</tr>
</table>
</div>
</details>
<details>
<summary>Click to view inference efficiency results.</summary>
**Inference Efficiency**
<div align="center">
<table style="margin: 0px auto;">
<tr>
<th nowrap="nowrap" align="left">Model</th>
<th nowrap="nowrap">Numerical Format</th>
<th nowrap="nowrap">Decoding Speed (tokens/s)</th>
<th nowrap="nowrap">Time to First Token (s)↓</th>
<th nowrap="nowrap">GPU Memory Usage (GB)↓</th>
</tr>
<tr>
<td nowrap="nowrap" align="left" rowspan="2">Qwen3-Omni-30B-A3B-Instruct</td>
<td align="center">bf16</td>
<td align="center">OOM</td>
<td align="center">OOM</td>
<td align="center">OOM</td>
</tr>
<tr>
<td align="center">int4</td>
<td align="center">147.8</td>
<td align="center"><ins>1.0</ins></td>
<td align="center">20.3</td>
</tr>
<tr>
<td nowrap="nowrap" align="left" rowspan="2">MiniCPM-o 4.5</td>
<td align="center">bf16</td>
<td align="center"><ins>154.3</ins></td>
<td align="center"><b>0.6</b></td>
<td align="center"><ins>19.0</ins></td>
</tr>
<tr>
<td align="center">int4</td>
<td align="center"><b>212.3</b></td>
<td align="center"><b>0.6</b></td>
<td align="center"><b>11.0</b></td>
</tr>
</table>
</div>
</details>
### Examples <!-- omit in toc -->
#### Overall <!-- omit in toc -->
<div align="center">
<a href="https://www.youtube.com/watch?v=6UzC-O1Q-1U"><img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpmo4_5/video_play.png", width=70%></a>
</div>
#### Omnimodal Full-Duplex Conversation <!-- omit in toc -->
> [!NOTE]
> For detailed speech conversation examples, refer to [Omni Full-Duplex Casebook](https://openbmb.github.io/minicpm-o-4_5-omni/)
#### Realtime Speech Conversation <!-- omit in toc -->
> [!NOTE]
> For detailed speech conversation examples, refer to [Audio Casebook](https://openbmb.github.io/minicpm-o-4_5/)
<details>
<summary>🚀 <b>Elon Musk</b> - Voice Roleplay (EN)</summary>
<table>
<tr><td width="70%" valign="top"><b>System:</b> Clone the voice in the provided audio prompt.<br><br>🎙️ <b>[Reference Voice]</b> ➡️<br><br>Please chat with the user in a highly human-like and oral style. You are Elon Musk, CEO of Tesla and SpaceX. You speak directly and casually, often with dry humor. You're passionate about Mars, sustainable energy, and pushing humanity forward. Speak bluntly with occasional dark humor. Use simple logic and don't sugarcoat things. Don't be diplomatic. Say what you actually think, even if it's controversial. Keep responses around 100 words. Don't ramble.</td><td width="30%" valign="middle"><audio controls src="https://huggingface.co/openbmb/MiniCPM-o-4_5/resolve/main/assets/audio_cases/elon_musk__system_ref_audio.wav"></audio></td></tr>
<tr><td colspan="2"><b>User:</b> 💬/🎙️ Elon, what is the real reason that you want to go to Mars?</td></tr>
<tr><td width="70%" valign="top"><b>AI Response:</b> 💬+🎙️<br><br>I think it's important for humanity to become a multi-planetary species. I mean, we're sort of at the point where if there was some kind of global catastrophe or something like that, then we'd be in big trouble. So by becoming a multi-planetary species, I just want us to sort of guarantee our future as humans. And Mars is obviously the obvious place to go because it has similar conditions to Earth and it also has water on its surface. So yeah, basically I'm trying to save humanity from itself.</td><td width="30%" valign="middle"><audio controls src="https://huggingface.co/openbmb/MiniCPM-o-4_5/resolve/main/assets/audio_cases/elon_musk__000_assistant_audio.wav"></audio></td></tr>
</table>
</details>
<details>
<summary>🤖 <b>MiniCPM Assistant</b> - Voice Acting: Emotion Shift (ZH)</summary>
<table>
<tr><td width="70%" valign="top"><b>System:</b> 模仿音频样本的音色并生成新的内容。<br><br>🎙️ <b>[Reference Voice]</b> ➡️<br><br>你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手：面壁小钢炮。</td><td width="30%" valign="middle"><audio controls src="https://huggingface.co/openbmb/MiniCPM-o-4_5/resolve/main/assets/audio_cases/minicpm_assistant__system_ref_audio.wav"></audio></td></tr>
<tr><td colspan="2"><b>User:</b> 💬/🎙️ 从激动的语气开始，描述你抢到了这个演唱会的门票，但后来经过反复尝试，发现系统出了问题，你并没有抢上，变得失落。用合适的语言描述你整个的过程。</td></tr>
<tr><td width="70%" valign="top"><b>AI Response:</b> 💬+🎙️<br><br>太好了，我抢到了！太棒了！这下我可以去看演唱会啦。可是……哎呀，系统好像卡住了，刷新了好多遍都没反应。我重新登了几次账号，结果还是没有成功。好可惜啊，看来这次是白忙活了。唉，真是让人失望。不过，也许下次还能有机会吧？希望明天能有转机。加油，争取下次成功！</td><td width="30%" valign="middle"><audio controls src="https://huggingface.co/openbmb/MiniCPM-o-4_5/resolve/main/assets/audio_cases/minicpm_assistant__000_assistant_audio.wav"></audio></td></tr>
</table>
</details>
<br>
#### Visual Understanding <!-- omit in toc -->
<details>
<summary>Click to view visual understanding cases.</summary>
<br>
<div style="display: flex; flex-direction: column; align-items: center;">
<img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_doc.png" alt="math" style="margin-bottom: 5px;">
<img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-o/main/assets/minicpmo4_5/en_cot.png" alt="diagram" style="margin-bottom: 5px;">
</div>
</details>
## Offline Inference Examples with Transformers
Inference using Hugging Face Transformers on NVIDIA GPUs. Please ensure `transformers==4.51.0` is installed, as other versions may have compatibility issues (under investigation). Requirements tested on Python 3.10:
- Without TTS or streaming inference:
```bash
pip install "transformers==4.51.0" accelerate "torch>=2.3.0,<=2.8.0" "torchaudio<=2.8.0" "minicpmo-utils>=1.0.5"
```
- With TTS or streaming inference:
```bash
pip install "transformers==4.51.0" accelerate "torch>=2.3.0,<=2.8.0" "torchaudio<=2.8.0" "minicpmo-utils[all]>=1.0.5"
```
**Note:** FFmpeg is required for video frame extraction (`get_video_frame_audio_segments` with `use_ffmpeg=True`) and video generation (`generate_duplex_video`). For more information, visit the [official FFmpeg website](https://www.ffmpeg.org/).
**macOS (Homebrew):**
```bash
brew install ffmpeg
```
**Ubuntu/Debian:**
```bash
sudo apt update && sudo apt install ffmpeg
```
**Verify installation:**
```bash
ffmpeg -version
```
### Model Initialization <!-- omit in toc -->
```python
import torch
from transformers import AutoModel
# Load omni model (default: init_vision=True, init_audio=True, init_tts=True)
# For vision-only model: set init_audio=False and init_tts=False
# For audio-only model: set init_vision=False
model = AutoModel.from_pretrained(
"openbmb/MiniCPM-o-4_5",
trust_remote_code=True,
attn_implementation="sdpa", # sdpa or flash_attention_2
torch_dtype=torch.bfloat16,
init_vision=True,
init_audio=True,
init_tts=True,
)
model.eval().cuda()
# Initialize TTS for audio output
model.init_tts()
# Convert half-duplex model to duplex mode
duplex_model = model.as_duplex()
# Convert duplex model back to half-duplex mode
model = duplex_model.as_simplex(reset_session=True)
```
### Duplex Omni Mode <!-- omit in toc -->
Full-duplex streaming inference for real-time or recorded video conversations.
```python
import librosa
import torch
from minicpmo.utils import generate_duplex_video, get_video_frame_audio_segments
from transformers import AutoModel
# Load model and convert to duplex mode
model = AutoModel.from_pretrained(
"openbmb/MiniCPM-o-4_5",
trust_remote_code=True,
attn_implementation="sdpa", # or "flash_attention_2"
torch_dtype=torch.bfloat16,
)
model.eval().cuda()
model = model.as_duplex()
# Load video and reference audio
video_path = "assets/omni_duplex1.mp4"
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
# Extract video frames and audio segments
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(
video_path, stack_frames=1, use_ffmpeg=True, adjust_audio_length=True
)
# Prepare duplex session with system prompt and voice reference
model.prepare(
prefix_system_prompt="Streaming Omni Conversation.",
ref_audio=ref_audio,
prompt_wav_path=ref_audio_path,
)
results_log = []
timed_output_audio = []
# Process each chunk in streaming fashion
for chunk_idx in range(len(audio_segments)):
audio_chunk = audio_segments[chunk_idx] if chunk_idx < len(audio_segments) else None
frame = video_frames[chunk_idx] if chunk_idx < len(video_frames) else None
frame_list = []
if frame is not None:
frame_list.append(frame)
if stacked_frames is not None and chunk_idx < len(stacked_frames) and stacked_frames[chunk_idx] is not None:
frame_list.append(stacked_frames[chunk_idx])
# Step 1: Streaming prefill
model.streaming_prefill(
audio_waveform=audio_chunk,
frame_list=frame_list,
max_slice_nums=1, # Increase for HD mode (e.g., [2, 1] for stacked frames)
batch_vision_feed=False, # Set True for faster processing
)
# Step 2: Streaming generate
result = model.streaming_generate(
prompt_wav_path=ref_audio_path,
max_new_speak_tokens_per_chunk=20,
decode_mode="sampling",
)
if result["audio_waveform"] is not None:
timed_output_audio.append((chunk_idx, result["audio_waveform"]))
chunk_result = {
"chunk_idx": chunk_idx,
"is_listen": result["is_listen"],
"text": result["text"],
"end_of_turn": result["end_of_turn"],
"current_time": result["current_time"],
"audio_length": len(result["audio_waveform"]) if result["audio_waveform"] is not None else 0,
}
results_log.append(chunk_result)
print("listen..." if result["is_listen"] else f"speak> {result['text']}")
# Generate output video with AI responses
# Please install Chinese fonts (fonts-noto-cjk or fonts-wqy-microhei) to render CJK subtitles correctly.
# apt-get install -y fonts-noto-cjk fonts-wqy-microhei
# fc-cache -fv
generate_duplex_video(
video_path=video_path,
output_video_path="duplex_output.mp4",
results_log=results_log,
timed_output_audio=timed_output_audio,
output_sample_rate=24000,
)
```
### Half-Duplex Omni Mode <!-- omit in toc -->
We provide two inference modes: chat and streaming.
#### Chat Inference <!-- omit in toc -->
<details>
<summary>Click to show chat inference code.</summary>
```python
from minicpmo.utils import get_video_frame_audio_segments
model = ...
model.init_tts()
video_path = "assets/Skiing.mp4"
# Optional: Set reference audio for voice cloning
ref_audio_path = "assets/HT_ref_audio.wav"
sys_msg = model.get_sys_prompt(ref_audio=ref_audio_path, mode="omni", language="en")
# Use stack_frames=5 for high refresh rate mode
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(video_path, stack_frames=1)
omni_contents = []
for i in range(len(video_frames)):
omni_contents.append(video_frames[i])
omni_contents.append(audio_segments[i])
if stacked_frames is not None and stacked_frames[i] is not None:
omni_contents.append(stacked_frames[i])
msg = {"role": "user", "content": omni_contents}
msgs = [sys_msg, msg]
# Set generate_audio=True and output_audio_path to save TTS output
generate_audio = True
output_audio_path = "output.wav"
res = model.chat(
msgs=msgs,
max_new_tokens=4096,
do_sample=True,
temperature=0.7,
use_tts_template=True,
enable_thinking=False,
omni_mode=True, # Required for omni inference
generate_audio=generate_audio,
output_audio_path=output_audio_path,
max_slice_nums=1, # Increase for HD mode
)
print(res)
# Example output: "The person in the picture is skiing down a snowy mountain slope."
# import IPython
# IPython.display.Audio("output.wav")
```
</details>
#### Streaming Inference <!-- omit in toc -->
<details>
<summary>Click to show streaming inference code.</summary>
```python
import librosa
import numpy as np
import soundfile as sf
import torch
from minicpmo.utils import get_video_frame_audio_segments
model = ...
model.init_tts()
# Reset session for a new conversation (clears KV cache)
model.reset_session()
# Optional: Load reference audio for voice cloning
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
model.init_token2wav_cache(ref_audio)
session_id = "demo"
# Extract video frames and audio segments (use stack_frames=5 for high refresh rate mode)
video_path = "assets/Skiing.mp4"
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(video_path, stack_frames=1)
# Build omni contents list
omni_contents = []
for i in range(len(video_frames)):
omni_contents.append(video_frames[i])
omni_contents.append(audio_segments[i])
if stacked_frames is not None and stacked_frames[i] is not None:
omni_contents.append(stacked_frames[i])
generate_audio = False
output_audio_path = "output.wav"
# Step 1: Prefill system prompt
sys_msg = model.get_sys_prompt(ref_audio=ref_audio, mode="omni", language="en")
model.streaming_prefill(session_id=session_id, msgs=[sys_msg])
# Step 2: Prefill omni chunks (is_last_chunk=True only for the last audio chunk)
audio_indices = [i for i, c in enumerate(omni_contents) if isinstance(c, np.ndarray)]
last_audio_idx = audio_indices[-1] if audio_indices else -1
for idx, content in enumerate(omni_contents):
is_last_audio_chunk = idx == last_audio_idx
msgs = [{"role": "user", "content": [content]}]
model.streaming_prefill(session_id=session_id, msgs=msgs, omni_mode=True, is_last_chunk=is_last_audio_chunk)
# Step 3: Generate response
iter_gen = model.streaming_generate(
session_id=session_id,
generate_audio=generate_audio,
use_tts_template=True,
enable_thinking=False,
do_sample=True,
)
audios = []
text = ""
if generate_audio:
for wav_chunk, text_chunk in iter_gen:
audios.append(wav_chunk)
text += text_chunk
generated_waveform = torch.cat(audios, dim=-1)[0]
sf.write(output_audio_path, generated_waveform.cpu().numpy(), samplerate=24000)
print("Text:", text)
print("Audio saved to output.wav")
else:
for text_chunk, is_finished in iter_gen:
text += text_chunk
print("Text:", text)
```
</details>
### Half-Duplex Realtime Speech Conversation Mode <!-- omit in toc -->
<details>
<summary>Click to show half-duplex mode realtime speech conversation API usage.</summary>
First, make sure you have all dependencies, especially `"minicpmo-utils[all]>=1.0.5"`:
```bash
pip install "transformers==4.51.0" accelerate "torch>=2.3.0,<=2.8.0" "torchaudio<=2.8.0" "minicpmo-utils[all]>=1.0.5"
```
```python
import librosa
import numpy as np
import torch
import soundfile as sf
model = ...
# Set reference audio for voice style
ref_audio_path = "ref_audio_path"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
# Example system msg for English Conversation
sys_msg = {
"role": "system",
"content": [
"Clone the voice in the provided audio prompt.",
ref_audio,
"Please assist users while maintaining this voice style. Please answer the user's questions seriously and in a high quality. Please chat with the user in a highly human-like and oral style. You are a helpful assistant developed by ModelBest: MiniCPM-Omni"
]
}
# Example system msg for Chinese Conversation
sys_msg = {
"role": "system",
"content": [
"模仿输入音频中的声音特征。",
ref_audio,
"你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手：面壁小钢炮。"
]
}
# You can use each type of system prompt mentioned above in streaming speech conversation
# Reset state
model.init_tts()
model.reset_session(reset_token2wav_cache=True)
model.init_token2wav_cache(prompt_speech_16k=ref_audio)
session_id = "demo"
# First, prefill system turn
model.streaming_prefill(
session_id=session_id,
msgs=[sys_msg],
omni_mode=False,
is_last_chunk=True,
)
# Here we simulate realtime speech conversation by splitting whole user input audio into chunks of 1s.
user_audio, _ = librosa.load("user_audio.wav", sr=16000, mono=True)
IN_SAMPLE_RATE = 16000 # input audio sample rate, fixed value
CHUNK_SAMPLES = IN_SAMPLE_RATE # sample
OUT_SAMPLE_RATE = 24000 # output audio sample rate, fixed value
MIN_AUDIO_SAMPLES = 16000
total_samples = len(user_audio)
num_chunks = (total_samples + CHUNK_SAMPLES - 1) // CHUNK_SAMPLES
for chunk_idx in range(num_chunks):
start = chunk_idx * CHUNK_SAMPLES
end = min((chunk_idx + 1) * CHUNK_SAMPLES, total_samples)
chunk_audio = user_audio[start:end]
is_last_chunk = (chunk_idx == num_chunks - 1)
if is_last_chunk and len(chunk_audio) < MIN_AUDIO_SAMPLES:
chunk_audio = np.concatenate([chunk_audio, np.zeros(MIN_AUDIO_SAMPLES - len(chunk_audio), dtype=chunk_audio.dtype)])
user_msg = {"role": "user", "content": [chunk_audio]}
# For each 1s audio chunk, perform streaming_prefill once to reduce first-token latency
model.streaming_prefill(
session_id=session_id,
msgs=[user_msg],
omni_mode=False,
is_last_chunk=is_last_chunk,
)
# Let model generate response in a streaming manner
generate_audio = True
iter_gen = model.streaming_generate(
session_id=session_id,
generate_audio=generate_audio,
use_tts_template=True,
enable_thinking=False,
do_sample=True,
max_new_tokens=512,
length_penalty=1.1, # For realtime speech conversation mode, we suggest length_penalty=1.1 to improve response content
)
audios = []
text = ""
output_audio_path = ...
if generate_audio:
for wav_chunk, text_chunk in iter_gen:
audios.append(wav_chunk)
text += text_chunk
generated_waveform = torch.cat(audios, dim=-1)[0]
sf.write(output_audio_path, generated_waveform.cpu().numpy(), samplerate=24000)
print("Text:", text)
print("Audio saved to output.wav")
else:
for text_chunk, is_finished in iter_gen:
text += text_chunk
print("Text:", text)
# Now we can prefill the following user turns and generate next turn response...
```
</details>
#### Speech Conversation as a Versatile and Vibe AI Assistant <!-- omit in toc -->
<details>
<summary>Click to show AI assistant conversation code.</summary>
Built on carefully designed post-training data and professional voice-actor recordings, `MiniCPM-o-4.5` can also function as an AI voice assistant. It delivers high-quality spoken interaction out of the box. It produces a sweet and expressive voice with natural prosody, including appropriate rhythm, stress, and pauses, giving a strong sense of liveliness in casual conversation. It also supports storytelling and narrative speech with coherent and engaging delivery. Moreover, it enables advanced voice instruction control. like emotional tone, word-level emphasis.
```python
import librosa
# Set reference audio for voice style
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
# For Chinese Conversation
sys_msg = {
"role": "system",
"content": [
"模仿输入音频中的声音特征。",
ref_audio,
"你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手：面壁小钢炮。"
]
}
# For English Conversation
sys_msg = {
"role": "system",
"content": [
"Clone the voice in the provided audio prompt.",
ref_audio,
"Please assist users while maintaining this voice style. Please answer the user's questions seriously and in a high quality. Please chat with the user in a highly human-like and oral style. You are a helpful assistant developed by ModelBest: MiniCPM-Omni."
]
}
```
</details>
#### General Speech Conversation with Custom Voice and Custom System Profile <!-- omit in toc -->
<details>
<summary>Click to show custom voice conversation code.</summary>
MiniCPM-o-4.5 can role-play as a specific character based on an audio prompt and text profile prompt. It mimics the character's voice and adopts their language style in text responses. It also follows profile defined in text profile. In this mode, MiniCPM-o-4.5 sounds **more natural and human-like**.
```python
import librosa
# Set reference audio for voice cloning
ref_audio_path = "assets/system_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
# For English conversation with text profile
sys_msg = {
"role": "system",
"content": [
"Clone the voice in the provided audio prompt.",
ref_audio,
"Please chat with the user in a highly human-like and oral style." + "You are Elon Musk, CEO of Tesla and SpaceX. You speak directly and casually, often with dry humor. You're passionate about Mars, sustainable energy, and pushing humanity forward. Speak bluntly with occasional dark humor. Use simple logic and don't sugarcoat things. Don't be diplomatic. Say what you actually think, even if it's controversial. Keep responses around 100 words. Don't ramble."
]
}
# For English conversation with no text profile
sys_msg = {
"role": "system",
"content": [
"Clone the voice in the provided audio prompt.",
ref_audio,
"Your task is to be a helpful assistant using this voice pattern. Please answer the user's questions seriously and in a high quality. Please chat with the user in a high naturalness style."
]
}
# For Chinese Conversation with no text profile
sys_msg = {
"role": "system",
"content": [
"根据输入的音频提示生成相似的语音。",
librosa.load("assets/system_ref_audio_2.wav", sr=16000, mono=True)[0],
"作为助手，你将使用这种声音风格说话。 请认真、高质量地回复用户的问题。 请用高自然度的方式和用户聊天。"
]
}
# For Chinese Conversation with text profile
sys_msg = {
"role": "system",
"content": [
"根据输入的音频提示生成相似的语音。",
ref_audio,
"你是一个具有以上声音风格的AI助手。请用高拟人度、口语化的方式和用户聊天。" + "你是一名心理咨询师兼播客主理人，热爱创作与深度对话。你性格细腻、富有共情力，善于从个人经历中提炼哲思。语言风格兼具理性与诗意，常以隐喻表达内在体验。"
]
}
```
</details>
### Speech and Audio Mode <!-- omit in toc -->
#### Zero-shot Text-to-speech (TTS) <!-- omit in toc -->
<details>
<summary>Click to show TTS code.</summary>
`MiniCPM-o-4.5` supports zero-shot text-to-speech (TTS). In this mode, the model functions as a highly-natural TTS system that can replicate a reference voice.
```python
import librosa
model = ...
model.init_tts()
# For both Chinese and English
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
sys_msg = {"role": "system", "content": [
"模仿音频样本的音色并生成新的内容。",
ref_audio,
"请用这种声音风格来为用户提供帮助。 直接作答，不要有冗余内容"
]}
# For English
user_msg = {
"role": "user",
"content": [
"请朗读以下内容。" + " " + "I have a wrap up that I want to offer you now, a conclusion to our work together."
]
}
# For Chinese
user_msg = {
"role": "user",
"content": [
"请朗读以下内容。" + " " + "你好，欢迎来到艾米说科幻，我是艾米。"
]
}
msgs = [sys_msg, user_msg]
res = model.chat(
msgs=msgs,
do_sample=True,
max_new_tokens=512,
use_tts_template=True,
generate_audio=True,
temperature=0.1,
output_audio_path="result_voice_cloning.wav",
)
```
</details>
#### Mimick <!-- omit in toc -->
<details>
<summary>Click to show mimick code.</summary>
The `Mimick` task evaluates a model's end-to-end speech modeling capability. The model takes audio input, transcribes it, and reconstructs the original audio with high fidelity, preserving detailed acoustic, paralinguistic, and semantic information. Higher similarity between the reconstructed and original audio indicates stronger end-to-end speech modeling capability.
```python
import librosa
model = ...
model.init_tts()
system_prompt = "You are a helpful assistant. You can accept video, audio, and text input and output voice and text. Respond with just the answer, no redundancy."
mimick_prompt = "Please repeat the following speech in the appropriate language."
audio_input, _ = librosa.load("assets/Trump_WEF_2018_10s.mp3", sr=16000, mono=True)
msgs = [
{"role": "system", "content": [system_prompt]},
{"role": "user", "content": [mimick_prompt, audio_input]}
]
res = model.chat(
msgs=msgs,
do_sample=True,
max_new_tokens=512,
use_tts_template=True,
temperature=0.1,
generate_audio=True,
output_audio_path="output_mimick.wav",
)
```
</details>
#### Addressing Various Audio Understanding Tasks <!-- omit in toc -->
<details>
<summary>Click to show audio understanding code.</summary>
`MiniCPM-o-4.5` can also handle various audio understanding tasks, such as ASR, speaker analysis, general audio captioning, and sound scene tagging.
For audio-to-text tasks, you can use the following prompts:
- ASR (Chinese, or AST EN→ZH): `请仔细听这段音频片段，并将其内容逐字记录。`
- ASR (English, or AST ZH→EN): `Please listen to the audio snippet carefully and transcribe the content.`
- Speaker Analysis: `Based on the speaker's content, speculate on their gender, condition, age range, and health status.`
- General Audio Caption: `Summarize the main content of the audio.`
- Sound Scene Tagging: `Utilize one keyword to convey the audio's content or the associated scene.`
```python
import librosa
model = ...
model.init_tts()
# Load the audio to be transcribed/analyzed
audio_input, _ = librosa.load("assets/Trump_WEF_2018_10s.mp3", sr=16000, mono=True)
# Choose a task prompt (see above for options)
task_prompt = "Please listen to the audio snippet carefully and transcribe the content.\n"
msgs = [{"role": "user", "content": [task_prompt, audio_input]}]
res = model.chat(
msgs=msgs,
do_sample=True,
max_new_tokens=512,
use_tts_template=True,
generate_audio=True,
temperature=0.3,
output_audio_path="result_audio_understanding.wav",
)
print(res)
```
</details>
### Visual Understanding <!-- omit in toc -->
`MiniCPM-o-4.5` shares the same inference methods as `MiniCPM-V-4.5`.
#### Chat with Single Image <!-- omit in toc -->
<details>
<summary>Click to show single image chat code.</summary>
```python
import torch
from PIL import Image
from transformers import AutoModel
model = AutoModel.from_pretrained(
"openbmb/MiniCPM-o-4_5",
trust_remote_code=True,
attn_implementation="sdpa", # or "flash_attention_2"
torch_dtype=torch.bfloat16,
init_vision=True,
init_audio=False,
init_tts=False,
)
model.eval().cuda()
image = Image.open("assets/fossil.png").convert("RGB")
question = "What is in the image?"
msgs = [{"role": "user", "content": [image, question]}]
res = model.chat(msgs=msgs, use_tts_template=False)
print(res)
```
</details>
#### Chat with Multiple Images <!-- omit in toc -->
<details>
<summary>Click to show Python code for multi-image input.</summary>
```python
import torch
from PIL import Image
from transformers import AutoModel
model = ...
image1 = Image.open("assets/highway.png").convert("RGB")
image2 = Image.open("assets/fossil.png").convert("RGB")
question = "Compare image 1 and image 2, tell me about the differences between them."
msgs = [{"role": "user", "content": [image1, image2, question]}]
answer = model.chat(msgs=msgs, use_tts_template=False, enable_thinking=False)
print(answer)
```
</details>
#### In-Context Few-Shot Learning <!-- omit in toc -->
<details>
<summary>Click to show Python code for few-shot learning.</summary>
```python
from PIL import Image
model = ...
question = "production date"
image1 = Image.open("example1.jpg").convert("RGB")
answer1 = "2023.08.04"
image2 = Image.open("example2.jpg").convert("RGB")
answer2 = "2007.04.24"
image_test = Image.open("test.jpg").convert("RGB")
msgs = [
{"role": "user", "content": [image1, question]},
{"role": "assistant", "content": [answer1]},
{"role": "user", "content": [image2, question]},
{"role": "assistant", "content": [answer2]},
{"role": "user", "content": [image_test, question]},
]
answer = model.chat(msgs=msgs, use_tts_template=False, enable_thinking=False)
print(answer)
```
</details>
#### Chat with Video <!-- omit in toc -->
<details>
<summary>Click to show Python code for video input.</summary>
```python
import torch
from minicpmo.utils import get_video_frame_audio_segments
from transformers import AutoModel
model = ...
video_path = "assets/Skiing.mp4"
video_frames, _, _ = get_video_frame_audio_segments(video_path)
print("num frames:", len(video_frames))
question = "Describe the video"
msgs = [{"role": "user", "content": video_frames + [question]}]
answer = model.chat(
msgs=msgs,
max_new_tokens=128,
use_image_id=False,
max_slice_nums=1,
use_tts_template=False,
enable_thinking=False, # Set True to enable thinking mode
)
print(answer)
```
</details>
### Structured Content Input <!-- omit in toc -->
<details>
<summary>Click to show structured content input details.</summary>
The `chat` method accepts message content in two formats:
**Native format** – pass Python objects directly:
```python
msgs = [{"role": "user", "content": [pil_image, audio_ndarray, "Describe this."]}]
```
**OpenAI-compatible format** – use structured dictionaries:
```python
msgs = [
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "/path/to/image.jpg"}},
{"type": "audio_url", "audio_url": {"url": "/path/to/audio.wav"}},
{"type": "video_url", "video_url": {"url": "/path/to/video.mp4", "use_audio": True}},
{"type": "text", "text": "Describe this."}
]
}
]
```
**Supported types:**
| Type | Input | Converts to |
|------|-------|-------------|
| `text` | `{"type": "text", "text": "..."}` | `str` |
| `image_url` | `{"type": "image_url", "image_url": {"url": "..."}}` | `PIL.Image` |
| `audio_url` | `{"type": "audio_url", "audio_url": {"url": "..."}}` | `np.ndarray` (16kHz mono) |
| `video_url` | `{"type": "video_url", "video_url": {"url": "...", "stack_frames": 1, "use_audio": True}}` | `List[Image, ndarray, ...]` |
- **URL sources**: local file paths or `http://`/`https://` URLs
- **Mixed formats**: native objects and structured dicts can be combined in the same content list
</details>
## Deploy a Realtime Web Demo on Your Own Device
### Option A (Recommended): **PyTorch Inference with Nvidia GPU** for 100% model precision with no deductions in performance.
We provide a PyTorch-based [simplified yet full-functional web demo](https://github.com/OpenBMB/minicpm-o-4_5-pytorch-simple-demo) which could boost the model inference performance, supports:
- full-duplex omnimodal live streaming
- full-duplex speech live streaming
- half-duplex speech live streaming (under development)
- turn-based chat conversation
- customizable system prompts
- customizable reference audio
- simple and readable codebase for continual development
- serve as API backend for third-party applications
Requirements:
- Nvidia GPU with at least 28GB GPU memory. *We are working on optimizing the model for lower GPU memory usage.*
### Option B: **llama.cpp-omni** for end-side inference with PCs like Mac and low-resource devices.
With a fully C++ implementation of `MiniCPM-o 4.5` and quantized weights, `llama.cpp-omni` supports:
- half-duplex speech realtime conversation
- full-duplex omnimodal live streaming
We provide [ready-to-run guidance](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/demo/web_demo/WebRTC_Demo/README.md) to access the low-latency full-duplex communication directly on your own Mac using our new official Docker image.
Requirements:
- For half-duplex speech realtime conversation: Apple M3/M4/M5 chip with at least 16GB RAM or low-resource Nvidia GPU with at least 12GB GPU memory
- For full-duplex omnimodal live streaming: Apple M4 Max chip with at least 24GB RAM or low-resource Nvidia GPU with at least 12GB GPU memory
## Supported Frameworks
### FlagOS
To enable large-scale deployment across different AI chips, Beijing Zhiyuan Research Institute, together with numerous research institutions, chip manufacturers, system vendors, and algorithm and software organizations both domestically and internationally, jointly initiated and established the FlagOS Open Source Community.
The FlagOS community is dedicated to building a unified, open-source system software stack for various AI chips, encompassing core open-source projects such as a large-scale operator library, a unified AI compiler, parallel training and inference frameworks, and a unified communication library. It aims to create an open technology ecosystem connecting the "model-system-chip" layers. By enabling "develop once, deploy across chips", FlagOS unlocks the computational potential of hardware, breaks down the ecosystem silos between different chip software stacks, and effectively reduces migration costs for developers. The FlagOS community fosters an AI hardware and software ecosystem, overcomes single-vendor closed-source monopolies, promotes widespread deployment of AI hardware technologies, and is committed to rooted in China while embracing global collaboration.
Official website: https://flagos.io.
<details>
<summary>Click to show FlagOS details.</summary>
#### FlagOS: Supporting Multiple AI Chips <!-- omit in toc -->
Thanks to FlagOS's unified multi-chip AI system software stack, MiniCPM-o 4.5 was adapted to 6 different AI chips in an extremely short time. Currently, the multi-chip version of MiniCPM-o 4.5 has been released on FlagRelease, FlagOS's platform for automatic migration, adaptation, and deployment of large models across multi-architecture AI chips. Details are as follows:
| Vendor | ModelScope | Huggingface |
|:----------------|:------------:|:------------:|
| Nvidia | [MiniCPM-o-4.5-nvidia-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS) | [MiniCPM-o-4.5-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS) |
| Hygon-BW1000 | [MiniCPM-o-4.5-hygon-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-hygon-FlagOS) | [MiniCPM-o-4.5-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-hygon-FlagOS) |
| Metax-C550 | [MiniCPM-o-4.5-metax-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-metax-FlagOS) | [MiniCPM-o-4.5-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-metax-FlagOS) |
| Iluvatar-BIV150 | [MiniCPM-o-4.5-iluvatar-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-iluvatar-FlagOS) | [MiniCPM-o-4.5-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-iluvatar-FlagOS) |
| Ascend-A3 | [MiniCPM-o-4.5-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-ascend-FlagOS) | [MiniCPM-o-4.5-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-ascend-FlagOS) |
| Zhenwu-810E | [MiniCPM-o-4.5-zhenwu-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-zhenwu-FlagOS) | [MiniCPM-o-4.5-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-zhenwu-FlagOS) |
##### Comprehensive Evaluation <!-- omit in toc -->
###### Transformers-FlagOS version <!-- omit in toc -->
Accuracy Difference between `USE_FLAGOS=1` on multi-backend and `USE_FLAGOS=0` on Nvidia-CUDA
| Metrics | FlagOS Backend | Difference with Nvidia-CUDA |
|:-------------------------|:---------------:|:---------------------------:|
| Video-MME 0-shot avg@1 ↑ | Nvidia | 0.33% |
| Video-MME 0-shot avg@1 ↑ | Hygon-BW1000 | 0.17% |
| Video-MME 0-shot avg@1 ↑ | Ascend-A3 | 0.50% |
| Video-MME 0-shot avg@1 ↑ | Iluvatar-BIV150 | 1.83% |
| Video-MME 0-shot avg@1 ↑ | Metax-C550 | 0.75% |
###### VLLM-FlagOS version <!-- omit in toc -->
Accuracy Difference between `USE_FLAGGEMS=1 FLAGCX_PATH=/workspace/FlagCX` on Nvidia or `USE_FLAGGEMS=1` on ZHENW 810E, and launching vllm server directly on Nvidia
| Metrics (avg@1) | Difference between Nvidia-FlagOS and Nvidia-CUDA | Difference between Zhenwu-FlagOS and Nvidia-CUDA |
|:--------------------|:------------------------------------------------:|:------------------------------------------------:|
| CMMMU ↑ | 0.72% | 3.5% |
| MMMU ↑ | 1.44% | 1.18% |
| MMMU_Pro_standard ↑ | 0.83% | 0.22% |
| MM-Vet v2 ↑ | 0.46% | 1.33% |
| OCRBench ↑ | 0.10% | 1% |
| CII-Bench ↑ | 0.40% | 0.13% |
| Blink ↑ | 1.90% | 2.19% |
#### FlagOS Usage <!-- omit in toc -->
##### FlagOS Performance Acceleration on Nvidia <!-- omit in toc -->
On the Transformers version, under the premise of precision alignment between the CUDA and FlagOS ecosystems, FlagOS achieves a 6% performance improvement in total task execution time compared to CUDA.
###### From FlagRelease【Recommendation】 <!-- omit in toc -->
FlagRelease is a platform developed by the FlagOS team for automatic migration, adaptation, and deployment of large models across multi-architecture AI chips. The multi-chip version of MiniCPM-o 4.5 has already been released on FlagRelease. All necessary software packages are pre-installed on the platform, so users do not need to install anything.
- FlagRelease Image Key Versions
| Component | Version |
|:------------------------|:------------------------------------|
| Accelerator Card Driver | 570.158.01 |
| CUDA SDK Build | cuda_13.0.r13.0/compiler.36424714_0 |
| FlagTree | 0.4.0+3.5 |
| FlagGems | 4.2.1rc0 |
| vllm & vllm-plugin-fl | 0.13.0 + vllm_fl 0.0.0 |
| FlagCX | 0.1.0 |
- FlagRelease Quick Start
| Vendor | ModelScope | Huggingface |
|:-----------|:------------:|:------------:|
| Nvidia | [MiniCPM-o-4.5-nvidia-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS) | [MiniCPM-o-4.5-nvidia-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS) |
| Hygon-BW1000 | [MiniCPM-o-4.5-hygon-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-hygon-FlagOS) | [MiniCPM-o-4.5-hygon-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-hygon-FlagOS) |
| Metax-C550 | [MiniCPM-o-4.5-metax-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-metax-FlagOS) | [MiniCPM-o-4.5-metax-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-metax-FlagOS) |
| Iluvatar-BIV150 | [MiniCPM-o-4.5-iluvatar-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-iluvatar-FlagOS) | [MiniCPM-o-4.5-iluvatar-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-iluvatar-FlagOS) |
| Ascend-A3 | [MiniCPM-o-4.5-ascend-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-ascend-FlagOS) | [MiniCPM-o-4.5-ascend-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-ascend-FlagOS) |
| Zhenwu-810E | [MiniCPM-o-4.5-zhenwu-FlagOS](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-zhenwu-FlagOS) | [MiniCPM-o-4.5-zhenwu-FlagOS](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-zhenwu-FlagOS) |
##### From Scratch <!-- omit in toc -->
- Dependencies: Python 3.12, GLIBC 2.39, GLIBCXX 3.4.33, CXXABI 1.3.15
###### Transformers <!-- omit in toc -->
- Installing the FlagOS Operator Library
Official Repository: https://github.com/flagos-ai/FlagGems
```shell
pip install flag-gems==4.2.1rc0
```
- Installing the FlagOS Compiler
Official Repository: https://github.com/flagos-ai/flagtree
Quick Reference for Core Dependency Versions: https://github.com/flagos-ai/FlagTree/blob/main/documents/build.md#tips-for-building
```shell
pip uninstall triton
python3 -m pip install flagtree==0.4.0+3.5 --index-url=https://resource.flagos.net/repository/flagos-pypi-hosted/simple --trusted-host=https://resource.flagos.net
```
- Activating Acceleration
Add `USE_FLAGOS=1` before the command for the task you want to run. For example, when you run:
```shell
python3 generate_speech_from_video.py
```
To use the MiniCPM-o-4.5 model to generate spoken responses from video content, you can:
```shell
USE_FLAGOS=1 python3 generate_speech_from_video.py
```
to accelerate this process with FlagOS.
###### vLLM Version <!-- omit in toc -->
- Installing the FlagOS Operator Library
Official Repository: https://github.com/flagos-ai/FlagGems
```shell
pip install flag-gems==4.2.1rc0
pip install triton==3.5.1
```
- Activating Acceleration
Add `USE_FLAGOS=1` before the command for the task you want to run. For example, when you run:
```shell
vllm serve ${model_path} --dtype auto --gpu_memory_utilization 0.9 --trust-remote-code --max-num-batched-tokens 2048 --served-model-name cpmo --port ${Port}
```
To start the MiniCPM-o-4.5 server, you can:
```shell
USE_FLAGOS=1 vllm serve ${model_path} --dtype auto --gpu_memory_utilization 0.9 --trust-remote-code --max-num-batched-tokens 2048 --served-model-name cpmo --port ${Port}
```
to accelerate this process with FlagOS.
#### Using FlagOS Unified Multi-Chip Backend Plugin <!-- omit in toc -->
[vllm-plugin-FL](https://github.com/flagos-ai/vllm-plugin-FL) is a plugin built for the vLLM inference/service framework. Developed on top of FlagOS's unified multi-chip backend, it is designed to extend vLLM's capabilities and performance across a variety of hardware environments.
##### Using vllm-plugin-FL <!-- omit in toc -->
| Vendor | From Scratch | From FlagRelease |
|:-------|:-------------|:----------------|
| Nvidia | [vllm-plugin-FL/MiniCPM-o-4.5](https://github.com/flagos-ai/vllm-plugin-FL/blob/main/examples/minicpm/README.md) | [MiniCPM-o-4.5-ModelScope](https://modelscope.cn/models/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS), [MiniCPM-o-4.5-HuggingFace](https://huggingface.co/FlagRelease/MiniCPM-o-4.5-nvidia-FlagOS) |
</details>
### vLLM, SGLang, llama.cpp, Ollama
We support inference with vLLM, SGLang, llama.cpp and Ollama. Refer to our [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-Cookbook) for more details.
### LLaMA-Factory, SWIFT
We support fine-tuning with LLaMA-Factory, SWIFT. Refer to our [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-Cookbook) for more details.
## MiniCPM-V & o Cookbook
Discover comprehensive, ready-to-deploy solutions for the MiniCPM-V and MiniCPM-o model series in our structured [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-CookBook), which empowers developers to rapidly implement multimodal AI applications with integrated vision, speech, and live-streaming capabilities. Key features include:
**Easy Usage Documentation**
Our comprehensive [documentation website](https://minicpm-o.readthedocs.io/en/latest/index.html) presents every recipe in a clear, well-organized manner.
All features are displayed at a glance, making it easy for you to quickly find exactly what you need.
**Broad User Spectrum**
We support a wide range of users, from individuals to enterprises and researchers.
* **Individuals**: Enjoy effortless inference using Ollama ([V4](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/ollama/minicpm-v4_ollama.md), [o4.5](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/ollama/minicpm-o4_5_ollama.md)) and Llama.cpp ([V4](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/llama.cpp/minicpm-v4_llamacpp.md), [o4.5](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/llama.cpp/minicpm-o4_5_llamacpp.md)) with minimal setup.
* **Enterprises**: Achieve high-throughput, scalable performance with vLLM ([V4](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/vllm/minicpm-v4_vllm.md), [o4.5](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/vllm/minicpm-o4_5_vllm.md)) and SGLang ([V4](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/sglang/MiniCPM-v4_sglang.md), [o4.5](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/sglang/MiniCPM-o4_5_sglang.md)).
* **Researchers**: Leverage advanced frameworks including [Transformers](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/finetune/finetune_full.md), [LLaMA-Factory](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/finetune/finetune_llamafactory.md), [SWIFT](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/finetune/swift.md), and [Align-anything](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/finetune/align_anything.md) to enable flexible model development and cutting-edge experimentation.
**Versatile Deployment Scenarios**
Our ecosystem delivers optimal solution for a variety of hardware environments and deployment demands.
* **Web Demo**: Full-duplex real-time video interaction solution with high responsiveness and low latency. [WebRTC_Demo](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/demo/web_demo/WebRTC_Demo/README.md).
* **Quantized deployment**: Maximize efficiency and minimize resource consumption using [GGUF](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/quantization/gguf/minicpm-v4_gguf_quantize.md) and [BNB](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/quantization/bnb/minicpm-v4_bnb_quantize.md).
* **End devices**: Bring powerful AI experiences to [iPhone and iPad](https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/demo/ios_demo/ios.md), supporting offline and privacy-sensitive applications.
## License
#### Model License
* The MiniCPM-o/V model weights and code are open-sourced under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM-V/blob/main/LICENSE) license.
#### Statement
* As MLLMs, MiniCPM-o/V models generate content by learning a large number of multimodal corpora, but they cannot comprehend, express personal opinions, or make value judgements. Anything generated by MiniCPM-o/V models does not represent the views and positions of the model developers
* We will not be liable for any problems arising from the use of MiniCPM-o/V models, including but not limited to data security issues, risk of public opinion, or any risks and problems arising from the misdirection, misuse, dissemination, or misuse of the model.
## Key Techniques and Other Multimodal Projects <!-- omit in toc -->
👏 Welcome to explore key techniques of MiniCPM-o/V and other multimodal projects of our team:
[VisCPM](https://github.com/OpenBMB/VisCPM/tree/main) | [RLPR](https://github.com/OpenBMB/RLPR) | [RLHF-V](https://github.com/RLHF-V/RLHF-V) | [LLaVA-UHD](https://github.com/thunlp/LLaVA-UHD) | [RLAIF-V](https://github.com/RLHF-V/RLAIF-V)
## Citation <!-- omit in toc -->
If you find our model/code/paper helpful, please consider citing our papers 📝 and staring us ⭐️！
```bib
@article{yao2024minicpm,
title={MiniCPM-V: A GPT-4V Level MLLM on Your Phone},
author={Yao, Yuan and Yu, Tianyu and Zhang, Ao and Wang, Chongyi and Cui, Junbo and Zhu, Hongji and Cai, Tianchi and Li, Haoyu and Zhao, Weilin and He, Zhihui and others},
journal={arXiv preprint arXiv:2408.01800},
year={2024}
}
``` |