Hugging Face's logo

kebengdou
/
Qwen3-Coder-Next-GGUF

Text Generation
GGUF
qwen3_next
unsloth
qwen
qwen3
imatrix
conversational
Model card Files
xet
 Community
kebengdou danielhanchen commited on
Commit
68877a9
·
0 Parent(s):

Duplicate from unsloth/Qwen3-Coder-Next-GGUF

Browse files

Co-authored-by: Daniel (Unsloth) <danielhanchen@users.noreply.huggingface.co>

Files changed (49) hide show
  1. .gitattributes +98 -0
  2. BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf +3 -0
  3. BF16/Qwen3-Coder-Next-BF16-00002-of-00004.gguf +3 -0
  4. BF16/Qwen3-Coder-Next-BF16-00003-of-00004.gguf +3 -0
  5. BF16/Qwen3-Coder-Next-BF16-00004-of-00004.gguf +3 -0
  6. Q4_1/Qwen3-Coder-Next-Q4_1-00001-of-00003.gguf +3 -0
  7. Q4_1/Qwen3-Coder-Next-Q4_1-00002-of-00003.gguf +3 -0
  8. Q4_1/Qwen3-Coder-Next-Q4_1-00003-of-00003.gguf +3 -0
  9. Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00001-of-00003.gguf +3 -0
  10. Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00002-of-00003.gguf +3 -0
  11. Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00003-of-00003.gguf +3 -0
  12. Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00001-of-00003.gguf +3 -0
  13. Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00002-of-00003.gguf +3 -0
  14. Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00003-of-00003.gguf +3 -0
  15. Q6_K/Qwen3-Coder-Next-Q6_K-00001-of-00003.gguf +3 -0
  16. Q6_K/Qwen3-Coder-Next-Q6_K-00002-of-00003.gguf +3 -0
  17. Q6_K/Qwen3-Coder-Next-Q6_K-00003-of-00003.gguf +3 -0
  18. Q8_0/Qwen3-Coder-Next-Q8_0-00001-of-00003.gguf +3 -0
  19. Q8_0/Qwen3-Coder-Next-Q8_0-00002-of-00003.gguf +3 -0
  20. Q8_0/Qwen3-Coder-Next-Q8_0-00003-of-00003.gguf +3 -0
  21. Qwen3-Coder-Next-IQ4_NL.gguf +3 -0
  22. Qwen3-Coder-Next-IQ4_XS.gguf +3 -0
  23. Qwen3-Coder-Next-MXFP4_MOE.gguf +3 -0
  24. Qwen3-Coder-Next-Q2_K.gguf +3 -0
  25. Qwen3-Coder-Next-Q2_K_L.gguf +3 -0
  26. Qwen3-Coder-Next-Q3_K_M.gguf +3 -0
  27. Qwen3-Coder-Next-Q3_K_S.gguf +3 -0
  28. Qwen3-Coder-Next-Q4_0.gguf +3 -0
  29. Qwen3-Coder-Next-Q4_K_M.gguf +3 -0
  30. Qwen3-Coder-Next-Q4_K_S.gguf +3 -0
  31. Qwen3-Coder-Next-UD-IQ1_M.gguf +3 -0
  32. Qwen3-Coder-Next-UD-IQ1_S.gguf +3 -0
  33. Qwen3-Coder-Next-UD-IQ2_XXS.gguf +3 -0
  34. Qwen3-Coder-Next-UD-IQ3_XXS.gguf +3 -0
  35. Qwen3-Coder-Next-UD-Q2_K_XL.gguf +3 -0
  36. Qwen3-Coder-Next-UD-Q3_K_XL.gguf +3 -0
  37. Qwen3-Coder-Next-UD-Q4_K_XL.gguf +3 -0
  38. Qwen3-Coder-Next-UD-TQ1_0.gguf +3 -0
  39. README.md +246 -0
  40. UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00001-of-00003.gguf +3 -0
  41. UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00002-of-00003.gguf +3 -0
  42. UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00003-of-00003.gguf +3 -0
  43. UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00003.gguf +3 -0
  44. UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00002-of-00003.gguf +3 -0
  45. UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00003-of-00003.gguf +3 -0
  46. UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00001-of-00003.gguf +3 -0
  47. UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00002-of-00003.gguf +3 -0
  48. UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00003-of-00003.gguf +3 -0
  49. imatrix_unsloth.gguf_file +3 -0
.gitattributes ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ BF16/Qwen3-Coder-Next-BF16-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
37
+ BF16/Qwen3-Coder-Next-BF16-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
38
+ BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
39
+ BF16/Qwen3-Coder-Next-BF16-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen3-Coder-Next-UD-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen3-Coder-Next-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen3-Coder-Next-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen3-Coder-Next-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen3-Coder-Next-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen3-Coder-Next-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen3-Coder-Next-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen3-Coder-Next-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
48
+ UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
49
+ UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Qwen3-Coder-Next-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Qwen3-Coder-Next-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Qwen3-Coder-Next-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
53
+ Q6_K/Qwen3-Coder-Next-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
54
+ Q6_K/Qwen3-Coder-Next-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
55
+ Qwen3-Coder-Next-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
56
+ Qwen3-Coder-Next-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
57
+ Qwen3-Coder-Next-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
58
+ Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
59
+ Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
60
+ Qwen3-Coder-Next-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
61
+ Qwen3-Coder-Next-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
62
+ Qwen3-Coder-Next-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
63
+ Q4_1/Qwen3-Coder-Next-Q4_1-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
64
+ Q4_1/Qwen3-Coder-Next-Q4_1-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
65
+ UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
66
+ UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
67
+ Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
68
+ Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
69
+ Q8_0/Qwen3-Coder-Next-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
70
+ Q8_0/Qwen3-Coder-Next-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
71
+ UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
72
+ UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
73
+ imatrix_unsloth.gguf_file filter=lfs diff=lfs merge=lfs -text
74
+ Qwen3-Coder-Next-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text
75
+ Q6_K/Qwen3-Coder-Next-Q6_K-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
76
+ Q6_K/Qwen3-Coder-Next-Q6_K-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
77
+ Q6_K/Qwen3-Coder-Next-Q6_K-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
78
+ UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
79
+ UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
80
+ UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
81
+ UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
82
+ UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
83
+ UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
84
+ Q8_0/Qwen3-Coder-Next-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
85
+ Q8_0/Qwen3-Coder-Next-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
86
+ Q8_0/Qwen3-Coder-Next-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
87
+ Q4_1/Qwen3-Coder-Next-Q4_1-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
88
+ Q4_1/Qwen3-Coder-Next-Q4_1-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
89
+ Q4_1/Qwen3-Coder-Next-Q4_1-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
90
+ UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
91
+ UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
92
+ UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
93
+ Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
94
+ Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
95
+ Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
96
+ Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
97
+ Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
98
+ Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49d3bfde5b8588f49d78610ef3a25af5c0ced0a4c4ab77bb8dca53062ba78a3
3
+ size 49004196032
BF16/Qwen3-Coder-Next-BF16-00002-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3258410cc3966a4888f5565eca2bc98e791b659a7041c3da419a751a5035a9a
3
+ size 49426194752
BF16/Qwen3-Coder-Next-BF16-00003-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b2f953e1bf2f162588430b0110cb0938245f3bf7d488ff8ca15790b5790d37
3
+ size 49447199840
BF16/Qwen3-Coder-Next-BF16-00004-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89280f8d77456c2ea0286646384bef74f96d06e4cdb9e65b7632aeb52f9ef499
3
+ size 11580824608
Q4_1/Qwen3-Coder-Next-Q4_1-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6997125c01586ef1778b90ce5f78fe51a5fa965dc719f31c7efd114e74081d36
3
+ size 5936320
Q4_1/Qwen3-Coder-Next-Q4_1-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121a419a310ff0c9545fb729a7f904ea610d8ca830a9c9b80b4c04f2404ec4ef
3
+ size 49715376992
Q4_1/Qwen3-Coder-Next-Q4_1-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ffcdbf9c258e69a140213af9ba1f1c90b4b3166f7f94ffccf04146f790ee07c
3
+ size 336109888
Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183e233cc93de594cf343d914bb2ba21f7ae252ac4699b52b83c1200327f4b11
3
+ size 5936320
Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfc3c900a2b6ed0d7d5c51397edd55261a0562a1ce64b62204c4576c3ecafd0
3
+ size 49604927264
Q5_K_M/Qwen3-Coder-Next-Q5_K_M-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b49c5c452924ca3b0864c6a32b3e5ebd14d6a063c5a89c976947347ed9a802c
3
+ size 7237023104
Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b3695c221fe4716b5d1397da1db7643d44dc697e03513b35c6a36aca479683
3
+ size 5936320
Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd131e37d7d656897004f434ced764c230cfc962232328ab907c4e6f3d4d1e2
3
+ size 49756868608
Q5_K_S/Qwen3-Coder-Next-Q5_K_S-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086f85116ece1e651a21f937268987214a9504dd5320842f6d450f765ba9c11f
3
+ size 5292475552
Q6_K/Qwen3-Coder-Next-Q6_K-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29fc953bb49f2f7857a7112dbe32dc17b7842c9afeaa4895a431437c692df50
3
+ size 5936320
Q6_K/Qwen3-Coder-Next-Q6_K-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28f4a3579b187ff5b2b67ae12cd7e060733775a6ccc9f2f8b59c3c17645b84b
3
+ size 49795838592
Q6_K/Qwen3-Coder-Next-Q6_K-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b08b8b13480d9ae269e77c09931dfbe45b8d002836da979d6b9078d0786ba61
3
+ size 15812217376
Q8_0/Qwen3-Coder-Next-Q8_0-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a7b3e9ac874942f06255527a0c4b884f777097e87e53c3e53922145f3ba8ed
3
+ size 5936320
Q8_0/Qwen3-Coder-Next-Q8_0-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491753e1ed8f20a5b898ae2f47ca58bed2707b56c00a3ec7c0b681b46d953ff8
3
+ size 49772613984
Q8_0/Qwen3-Coder-Next-Q8_0-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dced2b07a817f1e0c085fcc332b76c6e32bbab5e0c43311e0224f6249e03366
3
+ size 35033705312
Qwen3-Coder-Next-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18845b505e2393eb106635b3eaae37c26690497b20edfce8d457ccc0b521e76
3
+ size 45130344480
Qwen3-Coder-Next-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9039c9ebc67360f8760f32c8c72f800a74454b17c3fa287c0e2f34a55794e463
3
+ size 42676135968
Qwen3-Coder-Next-MXFP4_MOE.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fd6cfddf165a636debf1f928a67cec37484e82aa999a5240a11c319a4e8062
3
+ size 43741630240
Qwen3-Coder-Next-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac738bc947bc3470e37962c2ee0ab390fa953740e9873575695276980abad87
3
+ size 29224450080
Qwen3-Coder-Next-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c77ccf43a2ebf5f4d7232d268aaa5f8cb7f7397d6576de188576007859a84e4
3
+ size 29297379360
Qwen3-Coder-Next-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12ec74934e548b3e9cb80d05660a9a6a5af1a2aec6fbf5f9e9b4a36626aee75
3
+ size 38322487328
Qwen3-Coder-Next-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b076707e566e68fc8e307ff2a14cd2cfa7822e60467da31793e22c0cdc9e70c
3
+ size 34603089952
Qwen3-Coder-Next-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e981b4171e7e1c7bd73a6928d123d8d8591e8d9d64e1a29889752c336b4022a9
3
+ size 45330098208
Qwen3-Coder-Next-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6032d2f3b50a60f17ce8bf5a1d85c71af9b53b89c7978020ae7c660f29b090
3
+ size 48528320544
Qwen3-Coder-Next-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e490ddf8d25eb911557ee1f4604ab7207e43f00a2bcf16223040ca0484cdb5
3
+ size 45531949088
Qwen3-Coder-Next-UD-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde92c821c5afed845f19eaafe3fdd74781ca8325f95989f5a6f04f2efa85922
3
+ size 24155007008
Qwen3-Coder-Next-UD-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c98964d9dbc8aaba3153abe2aca35f6202a867e9e3ba2568b982621815d4ce
3
+ size 21508749344
Qwen3-Coder-Next-UD-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b479c178312cc7d2a133e1641779c5c7074f25bf1db7e7fe37f6da27b284edb
3
+ size 26285897760
Qwen3-Coder-Next-UD-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539ab176968feb2b94cc38afe094064c1fab430939de2a26f2fc86744c1fec31
3
+ size 32706197536
Qwen3-Coder-Next-UD-Q2_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a481e87afcb15e9d53442fa656b8c3b6b040da540c928495c9ba2b29637ae339
3
+ size 30228875296
Qwen3-Coder-Next-UD-Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb4dacced22b5304c8d8e1aafe80ae9e330ca01e440122a9c563fde9bd5753e
3
+ size 35474659360
Qwen3-Coder-Next-UD-Q4_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda283baab0b17b595a931957855b926d583094725e1add13068b0ba33c45ab5
3
+ size 44570617888
Qwen3-Coder-Next-UD-TQ1_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352049921f1dc861bf33fd03f5d2c25a08f248ee808179fe63ce16307357551c
3
+ size 18941835296
README.md ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - qwen3_next
4
+ - unsloth
5
+ - qwen
6
+ - qwen3
7
+ base_model:
8
+ - Qwen/Qwen3-Coder-Next
9
+ license: apache-2.0
10
+ license_link: https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE
11
+ pipeline_tag: text-generation
12
+ ---
13
+ <div>
14
+ <p style="margin-bottom: 0; margin-top: 0;">
15
+ <h1 style="margin-top: 0rem;">To Run Qwen3-Coder-Next locally - <a href="https://unsloth.ai/docs/models/qwen3-coder-next">Read our Guide!</a></h1>
16
+ </p>
17
+
18
+ <p style="margin-top: 0;margin-bottom: 0;">
19
+ <em><a href="https://unsloth.ai/docs/basics/unsloth-dynamic-2.0-ggufs">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
20
+ </p>
21
+ <div style="margin-top: 0;display: flex; gap: 5px; align-items: center; ">
22
+ <a href="https://github.com/unslothai/unsloth/">
23
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
24
+ </a>
25
+ <a href="https://discord.gg/unsloth">
26
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
27
+ </a>
28
+ <a href="https://unsloth.ai/docs/models/qwen3-coder-next">
29
+ <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
30
+ </a>
31
+ </div>
32
+ </div>
33
+
34
+ - **Feb 19 update**: Tool-calling should now be even better after llama.cpp fixes parsing.
35
+ - **Quantization benchmarks**: See third-party Aider, LiveCodeBench v6, MMLU Pro, GPQA [benchmarks for GGUFs here](https://unsloth.ai/docs/models/qwen3-coder-next#gguf-quantization-benchmarks).</h2>
36
+ - **Feb 4 update**: llama.cpp fixed a bug that caused Qwen to loop and have poor outputs.<br>We updated GGUFs - please re-download and update llama.cpp for improved outputs.</h2>
37
+
38
+ ## Qwen3-Coder-Next Usage Guidelines
39
+ - It is recommended to have >45GB unified memory or RAM/VRAM to run 4-bit quants.
40
+ - For best results, use any 2-bit XL quant or above (requires >30GB unified memory /combined RAM + VRAM).
41
+ - See how to run the model via [Claude Code & OpenAI Codex](https://unsloth.ai/docs/models/qwen3-coder-next#claude-codex).
42
+ - For complete detailed instructions (sampling parameters etc.), see our guide: [docs.unsloth.ai/models/qwen3-coder-next](https://unsloth.ai/docs/models/qwen3-coder-next)
43
+
44
+ ---
45
+
46
+ # Qwen3-Coder-Next
47
+
48
+ ## Highlights
49
+
50
+ Today, we're announcing **Qwen3-Coder-Next**, an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:
51
+
52
+ - **Super Efficient with Significant Performance**: With only 3B activated parameters (80B total parameters), it achieves performance comparable to models with 10–20x more active parameters, making it highly cost-effective for agent deployment.
53
+ - **Advanced Agentic Capabilities**: Through an elaborate training recipe, it excels at long-horizon reasoning, complex tool usage, and recovery from execution failures, ensuring robust performance in dynamic coding tasks.
54
+ - **Versatile Integration with Real-World IDE**: Its 256k context length, combined with adaptability to various scaffold templates, enables seamless integration with different CLI/IDE platforms (e.g., Claude Code, Qwen Code, Qoder, Kilo, Trae, Cline, etc.), supporting diverse development environments.
55
+
56
+ ![image/jpeg](https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen3-Coder-Next/benchmarks.png)
57
+
58
+ ![image/jpeg](https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen3-Coder-Next/swebench_pro.png)
59
+
60
+ ## Model Overview
61
+
62
+ **Qwen3-Coder-Next** has the following features:
63
+ - Type: Causal Language Models
64
+ - Training Stage: Pretraining & Post-training
65
+ - Number of Parameters: 80B in total and 3B activated
66
+ - Number of Parameters (Non-Embedding): 79B
67
+ - Hidden Dimension: 2048
68
+ - Number of Layers: 48
69
+ - Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> 1 \* (Gated Attention -> MoE))
70
+ - Gated Attention:
71
+ - Number of Attention Heads: 16 for Q and 2 for KV
72
+ - Head Dimension: 256
73
+ - Rotary Position Embedding Dimension: 64
74
+ - Gated DeltaNet:
75
+ - Number of Linear Attention Heads: 32 for V and 16 for QK
76
+ - Head Dimension: 128
77
+ - Mixture of Experts:
78
+ - Number of Experts: 512
79
+ - Number of Activated Experts: 10
80
+ - Number of Shared Experts: 1
81
+ - Expert Intermediate Dimension: 512
82
+ - Context Length: 262,144 natively
83
+
84
+ **NOTE: This model supports only non-thinking mode and does not generate ``<think></think>`` blocks in its output. Meanwhile, specifying `enable_thinking=False` is no longer required.**
85
+
86
+ For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwen.ai/blog?id=qwen3-coder-next), [GitHub](https://github.com/QwenLM/Qwen3-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).
87
+
88
+
89
+ ## Quickstart
90
+
91
+ We advise you to use the latest version of `transformers`.
92
+
93
+ The following contains a code snippet illustrating how to use the model generate content based on given inputs.
94
+ ```python
95
+ from transformers import AutoModelForCausalLM, AutoTokenizer
96
+
97
+ model_name = "Qwen/Qwen3-Coder-Next"
98
+
99
+ # load the tokenizer and the model
100
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
101
+ model = AutoModelForCausalLM.from_pretrained(
102
+ model_name,
103
+ torch_dtype="auto",
104
+ device_map="auto"
105
+ )
106
+
107
+ # prepare the model input
108
+ prompt = "Write a quick sort algorithm."
109
+ messages = [
110
+ {"role": "user", "content": prompt}
111
+ ]
112
+ text = tokenizer.apply_chat_template(
113
+ messages,
114
+ tokenize=False,
115
+ add_generation_prompt=True,
116
+ )
117
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
118
+
119
+ # conduct text completion
120
+ generated_ids = model.generate(
121
+ **model_inputs,
122
+ max_new_tokens=65536
123
+ )
124
+ output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
125
+
126
+ content = tokenizer.decode(output_ids, skip_special_tokens=True)
127
+
128
+ print("content:", content)
129
+ ```
130
+
131
+ **Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.**
132
+
133
+ For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
134
+
135
+ ## Deployment
136
+
137
+ For deployment, you can use the latest `sglang` or `vllm` to create an OpenAI-compatible API endpoint.
138
+
139
+ ### SGLang
140
+
141
+ [SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
142
+ SGLang could be used to launch a server with OpenAI-compatible API service.
143
+
144
+ `sglang>=v0.5.8` is required for Qwen3-Coder-Next, which can be installed using:
145
+ ```shell
146
+ pip install 'sglang[all]>=v0.5.8'
147
+ ```
148
+ See [its documentation](https://docs.sglang.ai/get_started/install.html) for more details.
149
+
150
+ The following command can be used to create an API endpoint at `http://localhost:30000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
151
+ ```shell
152
+ python -m sglang.launch_server --model Qwen/Qwen3-Coder-Next --port 30000 --tp-size 2 --tool-call-parser qwen3_coder```
153
+ ```
154
+
155
+ > [!Note]
156
+ > The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
157
+
158
+
159
+ ### vLLM
160
+
161
+ [vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
162
+ vLLM could be used to launch a server with OpenAI-compatible API service.
163
+
164
+ `vllm>=0.15.0` is required for Qwen3-Coder-Next, which can be installed using:
165
+ ```shell
166
+ pip install 'vllm>=0.15.0'
167
+ ```
168
+ See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details.
169
+
170
+ The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
171
+ ```shell
172
+ vllm serve Qwen/Qwen3-Coder-Next --port 8000 --tensor-parallel-size 2 --enable-auto-tool-choice --tool-call-parser qwen3_coder
173
+ ```
174
+
175
+ > [!Note]
176
+ > The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
177
+
178
+
179
+ ## Agentic Coding
180
+
181
+ Qwen3-Coder-Next excels in tool calling capabilities.
182
+
183
+ You can simply define or use any tools as following example.
184
+ ```python
185
+ # Your tool implementation
186
+ def square_the_number(num: float) -> dict:
187
+ return num ** 2
188
+
189
+ # Define Tools
190
+ tools=[
191
+ {
192
+ "type":"function",
193
+ "function":{
194
+ "name": "square_the_number",
195
+ "description": "output the square of the number.",
196
+ "parameters": {
197
+ "type": "object",
198
+ "required": ["input_num"],
199
+ "properties": {
200
+ 'input_num': {
201
+ 'type': 'number',
202
+ 'description': 'input_num is a number that will be squared'
203
+ }
204
+ },
205
+ }
206
+ }
207
+ }
208
+ ]
209
+
210
+ from openai import OpenAI
211
+ # Define LLM
212
+ client = OpenAI(
213
+ # Use a custom endpoint compatible with OpenAI API
214
+ base_url='http://localhost:8000/v1', # api_base
215
+ api_key="EMPTY"
216
+ )
217
+
218
+ messages = [{'role': 'user', 'content': 'square the number 1024'}]
219
+
220
+ completion = client.chat.completions.create(
221
+ messages=messages,
222
+ model="Qwen3-Coder-Next",
223
+ max_tokens=65536,
224
+ tools=tools,
225
+ )
226
+
227
+ print(completion.choices[0])
228
+ ```
229
+
230
+ ## Best Practices
231
+
232
+ To achieve optimal performance, we recommend the following sampling parameters: `temperature=1.0`, `top_p=0.95`, `top_k=40`.
233
+
234
+
235
+ ## Citation
236
+
237
+ If you find our work helpful, feel free to give us a cite.
238
+
239
+ ```
240
+ @techreport{qwen_qwen3_coder_next_tech_report,
241
+ title = {Qwen3-Coder-Next Technical Report},
242
+ author = {{Qwen Team}},
243
+ url = {https://github.com/QwenLM/Qwen3-Coder/blob/main/qwen3_coder_next_tech_report.pdf},
244
+ note = {Accessed: 2026-02-03}
245
+ }
246
+ ```
UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183e233cc93de594cf343d914bb2ba21f7ae252ac4699b52b83c1200327f4b11
3
+ size 5936320
UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f215a6f67175799dfa8dbd8a23a42fefda706fae9c791f0cd887670e5d481d
3
+ size 49699283136
UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45b96260b23e0e893b1136e4085c543d5d114ac4576e6935a1005d9d10ef104
3
+ size 7142454240
UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29fc953bb49f2f7857a7112dbe32dc17b7842c9afeaa4895a431437c692df50
3
+ size 5936320
UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d3ff1945594f4bb2656d1f94b63f08166a80b1d17e620da6f8bbedd9c02a4d
3
+ size 49862115456
UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3fa402a998a9700c71654f50751e16b6cd4dcd8515e88b271490af37c5e6115
3
+ size 18722638912
UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a7b3e9ac874942f06255527a0c4b884f777097e87e53c3e53922145f3ba8ed
3
+ size 5936320
UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b222065b1809a41bac05a7a0c79b75142b916f9bf71b9d80efd26fbf34a08bc3
3
+ size 49950429152
UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97089ba1b4b587b1a335d043b3667b4aa466d7531791f2ae9a7fe236042d41d9
3
+ size 43399982304
imatrix_unsloth.gguf_file ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071cacd3e65aefe55510a4bb1fea1d4a0a7d9cfc9f439c9896a877d243a0eb53
3
+ size 457007872