Running
1
llm-bench.io
📈
Live leaderboard of local LLMs — real-world quality & speed
None defined yet.
| Model | VRAM | Runs | Quality | Speed (tok/s) | Coding | Agent | Role-Play | Research | Updated |
|---|---|---|---|---|---|---|---|---|---|
Qwen3.8-27B
NVIDIA GeForce RTX 3090 |
24 GB | 4 | 88.6 | 49.0 | 84.2 | 89.6 | 92.4 | 88.3 | 2026-10-31 |
unsloth-qwen3.8:BALANCED
AMD Radeon Graphics |
24 GB | 3 | 86.6 | 38.1 | 80.0 | 87.8 | 92.0 | 86.7 | 2026-10-28 |
Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp
AMD Radeon RX 7800 XT |
16 GB | 3 | 86.2 | 37.5 | 83.8 | 86.9 | 87.8 | 86.2 | 2026-10-12 |
ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Swift-1.5-Qwen3.8-27B-Q4_K_S
AMD Radeon RX 7900 XTX |
24 GB | 3 | 85.8 | 72.4 | 82.3 | 81.9 | 90.4 | 88.7 | 2026-10-05 |
qwen3.8-flash-next-iq2_xs
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 4 | 85.7 | 75.7 | 80.7 | 87.3 | 89.4 | 85.4 | 2026-10-19 |
Ornith-1.5-35B-Q4_K_M
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 85.7 | 52.2 | 79.9 | 84.8 | 91.5 | 86.7 | 2026-10-27 |
Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 11 | 85.3 | 77.0 | 79.9 | 86.5 | 88.2 | 86.5 | 2026-10-05 |
bonsai-2:27b
AMD Radeon RX 9060 XT + AMD Radeon RX 7600/7600 XT/7600M XT/7600S/7700S / PRO W7600 |
16 GB | 3 | 85.3 | 25.4 | 77.2 | 88.2 | 88.8 | 87.1 | 2026-10-25 |
qwen3.8-27b-ud-q3_k_xl
NVIDIA GeForce RTX 5080 |
16 GB | 5 | 85.1 | 52.3 | 77.6 | 82.2 | 92.0 | 88.7 | 2026-10-10 |
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
NVIDIA GeForce RTX 4070 |
12 GB | 5 | 84.9 | 74.0 | 75.9 | 88.7 | 85.9 | 89.0 | 2026-10-24 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp
AMD Radeon RX 7800 XT |
16 GB | 15 | 84.8 | 48.4 | 75.1 | 85.0 | 93.3 | 85.7 | 2026-10-18 |
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 11 | 84.8 | 44.6 | 74.4 | 86.4 | 90.7 | 87.7 | 2026-10-27 |
Qwen3.8-27B-oQ6e-mtp
Apple M5 Max |
64 GB | 3 | 84.7 | 50.7 | 84.3 | 86.0 | 84.8 | 83.8 | 2026-10-10 |
mlx-community/Qwen3.8-27B-4bit
Apple M5 Max |
64 GB | 4 | 84.6 | 82.9 | 74.2 | 84.6 | 91.5 | 88.2 | 2026-10-21 |
Ornith-1.5-35B-A3B-oQ8e-mtp
Apple M5 Max |
64 GB | 3 | 84.5 | 126.3 | 81.7 | 87.2 | 86.4 | 82.8 | 2026-10-10 |
ukisai/Swift-Bonsai-2-GGUF:TQ1_0
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 84.5 | 64.7 | 79.7 | 86.1 | 89.4 | 82.7 | 2026-10-29 |
| 47 GB | 3 | 84.5 | 27.3 | 79.7 | 84.1 | 88.5 | 85.7 | 2026-10-28 | |
Qwen3.8-27B-oQ4e-mtp
Apple M5 Max |
64 GB | 8 | 84.2 | 41.8 | 75.8 | 84.2 | 91.2 | 85.7 | 2026-10-10 |
Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered
AMD Radeon RX 7800 XT |
16 GB | 4 | 84.2 | 35.5 | 77.8 | 79.8 | 91.9 | 87.3 | 2026-10-06 |
Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF-RVN-Q5_K_M-mtp
NVIDIA RTX A6000 |
47 GB | 3 | 84.2 | 29.7 | 78.5 | 83.9 | 88.4 | 86.0 | 2026-10-27 |
qwen3.8-27b-gsq3
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 84.1 | 114.4 | 77.9 | 84.8 | 87.2 | 86.5 | 2026-10-27 |
huihui-swift15-qwen3.8-27b
NVIDIA GeForce RTX 3080 + NVIDIA GeForce RTX 5080 |
16 GB | 4 | 84.0 | 118.8 | 78.7 | 83.4 | 88.9 | 84.8 | 2026-10-26 |
swift-1.5-iq3_xxs
AMD Radeon RX 7900 XTX |
24 GB | 5 | 84.0 | 53.1 | 78.1 | 84.8 | 88.5 | 84.7 | 2026-10-03 |
Qwen3.8-Flash-Next-oQ5e-mtp
Apple M5 Max |
128 GB | 6 | 83.9 | 70.2 | 73.9 | 85.1 | 92.1 | 84.7 | 2026-10-13 |
Qwen3.8-MXFP4
AMD Radeon AI PRO R9700 |
32 GB | 3 | 83.9 | 66.4 | 74.9 | 85.6 | 89.1 | 86.0 | 2026-10-23 |
qwen3.8:27b-q4_K_M
AMD Radeon RX 7800 XT |
16 GB | 6 | 83.9 | 26.4 | 78.7 | 80.5 | 92.3 | 84.2 | 2026-10-16 |
unsloth/Muse-Glimmer-30B-GGUF:UD-IQ3_XXS
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 83.7 | 37.6 | 69.0 | 90.6 | 91.6 | 83.4 | 2026-10-10 |
swift-1.5-qwen3.8-27b-uncensored
NVIDIA GeForce RTX 5060 Ti + NVIDIA GeForce RTX 5090 |
31 GB | 19 | 83.6 | 284.1 | 76.7 | 82.3 | 91.0 | 84.3 | 2026-10-11 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp
AMD Radeon RX 7800 XT |
16 GB | 5 | 83.4 | 39.6 | 80.6 | 83.5 | 83.7 | 86.0 | 2026-10-18 |
prism-ml/Ternary-Bonsai-2-27B-gguf:PTQ1_0
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 83.3 | 58.9 | 74.6 | 87.2 | 87.4 | 84.1 | 2026-10-11 |
ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S-mtp
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 83.3 | 46.9 | 73.3 | 83.1 | 89.7 | 87.2 | 2026-10-05 |
unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL
AMD Radeon AI PRO R9700 |
32 GB | 5 | 83.3 | 34.4 | 75.4 | 87.1 | 86.2 | 84.4 | 2026-10-13 |
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 12 | 83.2 | 78.9 | 77.7 | 88.1 | 82.8 | 84.4 | 2026-10-27 |
Ornith-1.5-35B-A3B-oQ4e-mtp
Apple M5 Pro |
48 GB | 5 | 83.2 | 74.2 | 77.7 | 85.2 | 85.0 | 84.9 | 2026-10-16 |
Qwen3.8-27B-oQ4e-mtp
Apple M4 Pro |
48 GB | 5 | 83.0 | 29.6 | 76.8 | 80.7 | 89.5 | 84.9 | 2026-10-20 |
Nex-N2.5-mini-IQ3_XXS
AMD Radeon RX 7800 XT |
16 GB | 4 | 82.9 | 106.2 | 77.4 | 87.5 | 85.3 | 81.5 | 2026-10-30 |
qwen3.8-27b-splash
Apple M4 Max |
128 GB | 97 | 82.7 | 73.5 | 77.3 | 78.2 | 90.0 | 85.3 | 2026-10-03 |
nex-n2.5-mini
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 82.7 | 66.1 | 77.0 | 81.5 | 87.8 | 84.5 | 2026-10-16 |
Qwen3.8-27B-oQ8e-mtp
Apple M5 Max |
64 GB | 32 | 82.7 | 46.5 | 74.3 | 84.2 | 87.7 | 84.6 | 2026-10-27 |
IsValorum/Ornith-1.5-35B-A3B-APEX-I-NanoPlus-GGUF
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 3 | 82.6 | 104.3 | 76.5 | 83.7 | 86.8 | 83.5 | 2026-10-05 |
ornith-1.5:35B
AMD Radeon Graphics |
24 GB | 3 | 82.6 | 79.5 | 73.9 | 87.8 | 82.9 | 86.0 | 2026-10-28 |
qwen3.8-flash-next-unsloth-ud-q4_k_xl
NVIDIA GeForce RTX 3090 |
24 GB | 4 | 82.3 | 24.5 | 63.9 | 86.5 | 92.5 | 86.4 | 2026-10-29 |
qwen3.8-flash-next-iq3_xxs
AMD Radeon RX 6950 XT |
16 GB | 4 | 82.2 | 50.5 | 66.0 | 86.0 | 91.5 | 85.3 | 2026-10-28 |
qwen3.8-flash-next-abliterated-iq3_s
AMD Radeon AI PRO R9700 |
32 GB | 4 | 82.1 | 57.5 | 69.2 | 83.0 | 91.0 | 85.4 | 2026-10-23 |
Ornith-1.5-35B-A3B.APEX-I-NanoPlus-ASCII-Condensed
AMD Radeon RX 7800 XT |
16 GB | 3 | 82.0 | 110.7 | 78.9 | 76.2 | 85.3 | 87.8 | 2026-10-09 |
muse-glimmer:30b-q4_K_M
AMD Radeon RX 7800 XT |
16 GB | 4 | 82.0 | 27.5 | 69.0 | 90.7 | 86.5 | 81.8 | 2026-10-16 |
Qwen3.8-Flash-Next-oQ4e-mix6-mtp
Apple M4 Max |
128 GB | 10 | 81.9 | 72.9 | 74.0 | 82.1 | 87.4 | 84.2 | 2026-10-13 |
SC117-Swift-IQ3_S
NVIDIA RTX A6000 |
47 GB | 3 | 81.6 | 94.9 | 55.9 | 90.5 | 91.4 | 88.5 | 2026-10-23 |
prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0
NVIDIA GeForce RTX 4070 |
12 GB | 4 | 81.6 | 57.0 | 73.8 | 87.5 | 81.7 | 83.4 | 2026-10-20 |
Ternary-Bonsai-2-27B-PTQ1_0
NVIDIA GeForce RTX 4070 |
12 GB | 5 | 81.6 | 50.7 | 62.0 | 87.4 | 91.1 | 85.9 | 2026-10-08 |
muse-glimmer-30b
Apple M5 Max |
64 GB | 3 | 81.6 | 30.8 | 72.5 | 82.8 | 88.5 | 82.8 | 2026-10-31 |
underdog-saluki-27b-1.0
AMD Radeon RX 6800/6800 XT / 6900 XT |
16 GB | 3 | 81.5 | 31.0 | 70.5 | 83.8 | 87.9 | 83.8 | 2026-10-14 |
qwen3.8-27b-splash
Apple M5 Max |
64 GB | 11 | 81.2 | 78.6 | 70.7 | 80.8 | 89.8 | 83.4 | 2026-10-14 |
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_XXS-mtp
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 81.2 | 42.4 | 64.6 | 85.7 | 88.8 | 85.7 | 2026-10-05 |
Tiel-Coder-35B-A3B-MLX-oQ6e-MTP
Apple M5 Max |
128 GB | 8 | 80.7 | 134.6 | 74.6 | 82.4 | 81.7 | 84.1 | 2026-10-17 |
Tiel-Coder-35B-A3B-MLX-oQ4e-MTP
Apple M5 Max |
128 GB | 6 | 80.2 | 174.6 | 79.7 | 81.5 | 76.0 | 83.4 | 2026-10-17 |
qwen3.8-flash-next-huihui-ud-q4_k_xl
AMD Radeon AI PRO R9700 |
32 GB | 4 | 80.0 | 33.0 | 60.2 | 88.5 | 86.5 | 84.7 | 2026-10-23 |
unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4_K_XL
Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 |
32 GB | 3 | 79.5 | 101.0 | 69.8 | 78.0 | 88.4 | 81.8 | 2026-10-04 |
Qwen3.6-35B-A3B-GSQ-hybrid
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 79.5 | 82.9 | 69.8 | 81.0 | 88.5 | 78.6 | 2026-10-04 |
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
Apple M5 Pro |
48 GB | 5 | 79.3 | 36.1 | 71.0 | 77.5 | 87.1 | 81.7 | 2026-10-16 |
qwen3.8-flash-next-unsloth-ud-iq4_xs
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 3 | 78.7 | 46.9 | 51.8 | 87.1 | 90.4 | 85.2 | 2026-10-19 |
swift-1.5-iq2_xs
AMD Radeon RX 7900 XTX |
24 GB | 5 | 77.7 | 80.2 | 61.9 | 72.9 | 92.3 | 83.8 | 2026-10-11 |
Qwen3.6-35B-A3B-UD-IQ2_XXS
AMD Radeon RX 7900 XTX |
24 GB | 12 | 77.6 | 209.8 | 71.9 | 75.6 | 83.3 | 79.7 | 2026-10-02 |
unsloth/Qwen3.6-35B-A3B-MTP-GGUF
NVIDIA GeForce RTX 3070 Ti |
8 GB | 3 | 77.6 | 52.3 | 75.8 | 74.5 | 83.1 | 77.1 | 2026-10-14 |
pfeifferj/Ornith-1.5-35B-A3B-GSQ-RCO-GGUF:3bit
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 10 | 77.4 | 88.5 | 73.9 | 63.7 | 86.9 | 85.1 | 2026-10-08 |
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL
Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 |
32 GB | 4 | 77.2 | 35.8 | 44.8 | 87.8 | 89.7 | 86.3 | 2026-10-10 |
Qwen3.8-27B-MTPLX-Optimized-Speed
Apple M4 Pro |
48 GB | 3 | 77.0 | 24.1 | 63.1 | 82.7 | 80.7 | 81.6 | 2026-10-18 |
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1
NVIDIA GeForce RTX 4050 Laptop GPU |
6 GB | 7 | 76.7 | 26.4 | 68.4 | 78.4 | 84.3 | 75.8 | 2026-10-25 |
unsloth-qwen3.8:TOOLING
AMD Radeon Graphics |
24 GB | 4 | 76.6 | 34.1 | 59.2 | 81.6 | 83.9 | 81.5 | 2026-10-28 |
tiel-coder-35b
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 76.2 | 76.0 | 75.4 | 79.4 | 73.2 | 76.7 | 2026-10-16 |
MiniCPM-V-4.7-35B-A3B.APEX-I-NanoPlus-V2.1
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 76.1 | 92.7 | 61.8 | 84.6 | 79.9 | 78.0 | 2026-10-19 |
swift-1.5-iq3_s
NVIDIA GeForce RTX 5090 |
32 GB | 3 | 76.0 | 206.7 | 51.7 | 83.4 | 86.8 | 82.1 | 2026-10-23 |
gpt-oss:20b
AMD Radeon RX 9060 XT + AMD Radeon RX 7600/7600 XT/7600M XT/7600S/7700S / PRO W7600 |
16 GB | 3 | 76.0 | 64.5 | 73.0 | 83.0 | 72.8 | 75.3 | 2026-10-27 |
prism-ml/Ternary-Bonsai-2-27B-gguf:PQ2_0
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 7 | 75.8 | 41.5 | 48.2 | 84.4 | 86.0 | 84.5 | 2026-10-05 |
nvidia-nemotron-3.5-lightning-30b-a3b
Apple M5 Max |
64 GB | 4 | 75.7 | 111.4 | 66.5 | 85.9 | 71.5 | 78.7 | 2026-10-11 |
Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit
Apple M4 Pro |
48 GB | 7 | 75.6 | 121.2 | 71.4 | 73.6 | 83.6 | 73.8 | 2026-10-21 |
ornith15-heretic-mini
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 75.6 | 72.8 | 59.3 | 81.3 | 86.5 | 75.4 | 2026-10-16 |
qwen3.8-27b-gsq-rco@iq2_xs
AMD Radeon RX 7900 GRE |
16 GB | 3 | 75.6 | 31.2 | 78.0 | 64.6 | 82.7 | 77.2 | 2026-10-08 |
qwen38-27b-turbo
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 75.6 | 29.5 | 71.2 | 75.6 | 78.9 | 76.7 | 2026-10-15 |
Qwopus3.8-27B-Flash-V2-oQ8e-mtp
Apple M5 Max |
64 GB | 3 | 75.5 | 46.5 | 56.5 | 80.1 | 84.9 | 80.6 | 2026-10-11 |
nemotron-3.5-bolt
AMD Radeon AI PRO R9700 |
32 GB | 3 | 75.3 | 112.4 | 60.2 | 83.7 | 77.4 | 80.0 | 2026-10-23 |
Qwen3.6-35B-A3B-4bit
Apple M4 Pro |
48 GB | 3 | 75.1 | 118.4 | 69.3 | 77.4 | 75.0 | 78.7 | 2026-10-19 |
IsValorum/Occamy-1.0-APEX-I-NanoPlus-GGUF
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 8 | 74.9 | 104.0 | 56.0 | 75.0 | 84.5 | 84.0 | 2026-10-06 |
Qwen3.8-27B-Uncensored-MLX
Apple M4 Pro |
48 GB | 4 | 74.7 | 26.2 | 54.3 | 77.8 | 83.8 | 83.0 | 2026-10-20 |
qwen3.8-flash-next-unsloth-ud-iq4_xs
NVIDIA GeForce RTX 3090 |
24 GB | 4 | 74.6 | 46.3 | 38.0 | 90.8 | 94.2 | 75.5 | 2026-10-29 |
Ornith-1.5-35B-A3B.APEX-I-NanoPlus
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 74.5 | 110.5 | 81.1 | 61.2 | 69.2 | 86.4 | 2026-10-18 |
protoLabsAI/Ornith-1.5-9B-MTP-GGUF:Q5_K_M
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 74.5 | 78.9 | 53.8 | 76.4 | 82.5 | 85.5 | 2026-10-06 |
qwen3.8-flash-next-gyro-s-abliterated
AMD Radeon AI PRO R9700 |
32 GB | 4 | 74.4 | 77.3 | 60.5 | 71.8 | 87.3 | 78.2 | 2026-10-23 |
recursivesi/flint
Apple M5 Max |
64 GB | 4 | 74.3 | 107.4 | 54.4 | 78.7 | 84.4 | 79.8 | 2026-10-30 |
Qwopus3.8-27B-Flash-V2-oQ4e-mtp
Apple M5 Max |
64 GB | 3 | 74.3 | 66.9 | 56.9 | 76.8 | 84.3 | 79.3 | 2026-10-11 |
Qwen3.8-27B-UD-Q3_K_XL
NVIDIA GeForce RTX 5070 Ti |
16 GB | 12 | 74.2 | 60.5 | 42.1 | 85.2 | 90.2 | 79.2 | 2026-10-28 |
openbmb/MiniCPM-V-4.7-35B-A3B-gguf
NVIDIA GeForce RTX 3070 Ti |
8 GB | 4 | 73.7 | 51.8 | 66.7 | 83.2 | 73.3 | 71.7 | 2026-10-14 |
text-model
NVIDIA RTX A2000 12GB + NVIDIA RTX 2000 Ada Generation |
16 GB | 8 | 73.2 | 91.3 | 68.0 | 72.0 | 81.2 | 71.7 | 2026-10-14 |
cyankiwi/gemma-4-31B-it-AWQ-4bit
NVIDIA GeForce RTX 3080 Ti + NVIDIA GeForce RTX 3080 |
20 GB | 4 | 73.2 | 32.3 | 61.5 | 82.5 | 79.1 | 69.8 | 2026-10-22 |
Cyber-Tiel-Coder-35B-A3B-UD-IQ3_S
AMD Radeon 680M |
4 GB | 5 | 72.9 | 11.2 | 55.9 | 80.2 | 81.5 | 74.0 | 2026-10-31 |
NeoHorse-1-4B-GGUF
NVIDIA RTX A6000 |
47 GB | 3 | 72.8 | 104.9 | 57.2 | 81.2 | 74.9 | 77.9 | 2026-10-22 |
NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-NVFP4
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 11 | 72.7 | 65.6 | 65.5 | 81.5 | 80.4 | 63.6 | 2026-10-31 |
Qwen3.8-9B-Q4_K_M
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 5 | 72.7 | 34.5 | 57.8 | 81.3 | 78.8 | 72.9 | 2026-10-30 |
Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF
NVIDIA GeForce RTX 3070 Ti |
8 GB | 3 | 72.5 | 57.3 | 72.8 | 57.1 | 85.2 | 74.9 | 2026-10-14 |
ornith-1.5-9b
AMD Radeon RX 9050 / 9060 XT |
16 GB | 12 | 72.2 | 92.1 | 60.3 | 62.6 | 83.7 | 82.4 | 2026-10-20 |
NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K-DFLASH-BF16
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 5 | 72.2 | 61.2 | 65.9 | 77.2 | 80.5 | 65.1 | 2026-10-30 |
Qwen3.6-35B-A3B-oQ4e-mtp
Apple M4 Pro |
48 GB | 21 | 72.0 | 97.8 | 66.9 | 65.4 | 79.7 | 76.2 | 2026-10-19 |
Tiel-Coder-35B-A3B-MLX-oQ4e-MTP
Apple M4 Max |
64 GB | 3 | 71.8 | 153.1 | 67.6 | 83.7 | 53.4 | 82.4 | 2026-10-22 |
mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 71.6 | 62.8 | 56.5 | 74.0 | 87.1 | 68.8 | 2026-10-12 |
qwen3.5-4b@q6_k
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 71.5 | 28.9 | 54.8 | 73.9 | 79.1 | 78.1 | 2026-10-15 |
ggml-org/gpt-oss-20b-GGUF
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 3 | 71.4 | 142.1 | 72.3 | 78.8 | 57.6 | 76.8 | 2026-10-05 |
gemma4:26b-a4b-it-qat
AMD Radeon RX 7800 XT |
16 GB | 3 | 71.3 | 72.2 | 64.8 | 75.7 | 76.2 | 68.5 | 2026-10-09 |
unsloth/gemma-4-31B-it-qat-GGUF:UD-Q4_K_XL
AMD Radeon AI PRO R9700 |
32 GB | 7 | 71.3 | 49.0 | 66.0 | 76.5 | 72.7 | 70.1 | 2026-10-13 |
Qwen3.8-27B-4bit
Apple M4 Pro |
48 GB | 3 | 71.1 | 28.9 | 53.5 | 66.6 | 84.7 | 79.7 | 2026-10-20 |
huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF
NVIDIA GeForce RTX 3070 Ti |
8 GB | 7 | 70.9 | 58.6 | 67.3 | 68.3 | 86.8 | 61.4 | 2026-11-01 |
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 70.9 | 46.3 | 62.6 | 81.1 | 77.6 | 62.3 | 2026-10-30 |
NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 70.9 | 42.0 | 61.5 | 79.6 | 80.7 | 61.5 | 2026-10-30 |
gpt-oss-120b-Sonnet-Reasoning-Distilled
Apple M4 Max |
128 GB | 10 | 70.8 | 82.3 | 67.9 | 74.7 | 70.6 | 69.9 | 2026-10-13 |
google/gemma-4-26b-a4b
Apple M5 Max |
64 GB | 4 | 70.7 | 114.1 | 67.8 | 78.8 | 75.7 | 60.4 | 2026-10-30 |
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MTP-GGUF
NVIDIA GeForce RTX 3070 Ti |
8 GB | 4 | 70.7 | 51.7 | 69.5 | 68.5 | 74.4 | 70.3 | 2026-10-04 |
unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q5_K_XL
AMD Radeon AI PRO R9700 |
32 GB | 4 | 70.2 | 67.1 | 64.2 | 78.1 | 78.7 | 60.0 | 2026-10-13 |
peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 69.6 | 91.2 | 61.9 | 79.5 | 67.1 | 69.8 | 2026-10-15 |
gemma4-26b-opus-distill
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 69.6 | 63.0 | 59.6 | 71.1 | 78.5 | 69.1 | 2026-10-16 |
gemma4-26b-uncensored-mtp
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 4 | 69.6 | 58.3 | 64.7 | 67.7 | 80.6 | 65.7 | 2026-10-16 |
gemma4-26b-a4b-qat
NVIDIA RTX A2000 12GB + NVIDIA GeForce RTX 2080 Ti |
12 GB | 3 | 69.2 | 63.1 | 65.0 | 69.4 | 75.7 | 66.5 | 2026-10-16 |
unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 4 | 69.0 | 121.1 | 57.8 | 85.1 | 70.3 | 62.7 | 2026-10-28 |
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL-DFLASH-NVFP4
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 69.0 | 61.1 | 63.0 | 77.8 | 75.3 | 60.0 | 2026-10-30 |
ornith-ai/Ornith-1.5-9B-GGUF:Q4_K_M
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 68.7 | 75.2 | 68.7 | 39.7 | 86.5 | 80.0 | 2026-10-13 |
IFM/K2-Horizon-7B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 68.1 | 69.5 | 25.8 | 86.9 | 77.4 | 82.4 | 2026-10-15 |
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF:MXFP4_MOE
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 9 | 68.0 | 168.0 | 58.4 | 72.7 | 71.8 | 69.1 | 2026-10-10 |
mellum2.1-12b-a2.5b-thinking
Apple M5 Max |
64 GB | 3 | 67.9 | 97.1 | 52.6 | 75.5 | 69.5 | 74.0 | 2026-10-09 |
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M
NVIDIA GeForce RTX 4070 |
12 GB | 8 | 67.1 | 132.9 | 54.9 | 71.5 | 70.6 | 71.3 | 2026-10-13 |
Jan-v3.5-4B-Q4_K_XL
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 67.1 | 73.4 | 40.7 | 81.6 | 86.0 | 60.0 | 2026-10-27 |
unsloth/gemma-4-E4B-it-qat-GGUF
NVIDIA GeForce RTX 3070 Ti |
8 GB | 3 | 67.0 | 176.2 | 50.7 | 79.3 | 74.1 | 63.8 | 2026-10-04 |
LFM2.5-24B-A2B-MLX-8bit
Apple M5 Max |
64 GB | 5 | 67.0 | 122.9 | 66.4 | 51.5 | 77.9 | 72.1 | 2026-10-15 |
gemma-4-E4B-it-Q4_0
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 11 | 66.6 | 88.5 | 55.2 | 71.1 | 74.0 | 66.4 | 2026-10-29 |
Mellum2-12B-A2.5B-Instruct-MXFP4_MOE
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 66.2 | 86.6 | 59.1 | 72.6 | 72.9 | 60.2 | 2026-10-31 |
Qwen3.8-4B-Q5_K_M
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 5 | 65.5 | 52.7 | 46.1 | 64.7 | 77.6 | 73.7 | 2026-10-29 |
unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
AMD Radeon AI PRO R9700 |
32 GB | 3 | 65.3 | 113.7 | 59.7 | 69.9 | 82.6 | 49.0 | 2026-10-17 |
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 6 | 64.8 | 125.7 | 56.5 | 59.8 | 72.5 | 70.3 | 2026-10-13 |
Ministral-3-8B-Instruct-2512-Q4_K_M
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 6 | 64.4 | 34.9 | 53.1 | 61.7 | 73.2 | 69.4 | 2026-10-31 |
Spark-X2.6-4B-Q8_0
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 24 | 63.5 | 39.4 | 48.9 | 76.6 | 65.6 | 63.0 | 2026-11-01 |
google/gemma-4-e2b
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 4 | 62.4 | 105.4 | 45.8 | 65.2 | 73.4 | 65.3 | 2026-10-12 |
bartowski/Ornith-1.5-9B-GGUF:IQ4_XS
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 61.1 | 70.3 | 52.0 | 32.7 | 85.4 | 74.4 | 2026-10-10 |
Spark-X2.6-4B-Q4_K_M
NVIDIA GeForce RTX 3060 |
12 GB | 4 | 61.1 | 69.0 | 34.6 | 78.4 | 65.1 | 66.1 | 2026-10-20 |
qwen3.8-4b-distill
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 59.3 | 32.0 | 31.9 | 64.8 | 70.6 | 69.9 | 2026-10-13 |
ministral-3-8b-instruct-2512
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 59.0 | 8.7 | 39.6 | 67.8 | 77.7 | 50.9 | 2026-10-17 |
LiquidAI/LFM3-1.7B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 57.9 | 251.4 | 28.7 | 76.0 | 48.8 | 78.0 | 2026-10-29 |
prism-ml/Ternary-Bonsai-2-9B-gguf:PTQ1_0
NVIDIA GeForce RTX 4070 |
12 GB | 4 | 57.8 | 150.0 | 28.2 | 72.0 | 63.4 | 67.6 | 2026-10-19 |
inclusionAI/Ling-3.0-tiny-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 56.7 | 210.6 | 45.0 | 72.2 | 40.5 | 69.0 | 2026-10-29 |
prism-ml/Ternary-Bonsai-2-9B-gguf:PQ2_0
NVIDIA GeForce RTX 4070 |
12 GB | 22 | 55.7 | 173.8 | 25.7 | 65.0 | 66.8 | 65.2 | 2026-10-16 |
speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q5_K_M
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 55.1 | 58.3 | 23.1 | 75.4 | 71.5 | 50.4 | 2026-10-10 |
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 10 | 53.9 | 146.4 | 17.6 | 72.0 | 57.9 | 68.1 | 2026-10-16 |
prism-ml/Ternary-Bonsai-2-4B-gguf:Q2_0
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 52.7 | 222.0 | 20.0 | 61.3 | 72.4 | 57.1 | 2026-10-19 |
Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M
NVIDIA GeForce RTX 2080 Ti |
11 GB | 3 | 52.6 | 62.5 | 40.0 | 57.9 | 55.6 | 56.8 | 2026-10-16 |
mistralai/ministral-3-3b
NVIDIA GeForce RTX 2050 |
4 GB | 7 | 52.2 | 24.8 | 34.4 | 52.1 | 66.7 | 55.5 | 2026-10-30 |
nvidia/nemotron-3-nano-4b
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 4 | 52.0 | 78.3 | 16.1 | 66.5 | 61.9 | 63.5 | 2026-10-12 |
prism-ml/Ternary-Bonsai-2-9B-gguf:Q2_0
NVIDIA GeForce RTX 4070 |
12 GB | 4 | 51.8 | 145.8 | 18.4 | 59.7 | 71.3 | 57.7 | 2026-10-19 |
prism-ml/Ternary-Bonsai-2-4B-gguf:PQ2_0
NVIDIA GeForce RTX 4070 |
12 GB | 13 | 51.0 | 246.2 | 22.4 | 61.4 | 63.5 | 56.7 | 2026-10-19 |
gemma-3-4b-it
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 3 | 50.8 | 12.7 | 30.6 | 43.7 | 78.9 | 50.2 | 2026-10-21 |
ministral-3-3b-instruct-2512
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 4 | 50.4 | 13.1 | 32.7 | 51.6 | 69.4 | 48.0 | 2026-10-31 |
qwen3.5-4B-super-coder.Q4_0
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 3 | 50.3 | 66.0 | 30.0 | 46.4 | 69.8 | 55.1 | 2026-11-01 |
granite-3.3-8b-instruct
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 49.9 | 13.6 | 15.8 | 72.0 | 64.6 | 47.1 | 2026-10-26 |
prism-ml/Ternary-Bonsai-8B-gguf:Q2_0
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 48.5 | 151.1 | 21.2 | 64.0 | 67.7 | 41.1 | 2026-10-10 |
llama3.1:latest
NVIDIA GeForce RTX 4080 SUPER |
16 GB | 4 | 47.9 | 99.1 | 31.6 | 61.5 | 55.4 | 43.3 | 2026-10-31 |
qwen/qwen3-1.7b
NVIDIA GeForce RTX 2050 |
4 GB | 4 | 47.9 | 57.5 | 21.3 | 67.5 | 60.5 | 42.2 | 2026-10-30 |
openbmb/MiniCPM5-2B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 4 | 47.4 | 198.0 | 15.8 | 53.0 | 44.3 | 76.2 | 2026-10-14 |
Llama-3.1-Tulu-3-8B-Q4_K_M
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 47.3 | 42.2 | 29.1 | 47.1 | 62.7 | 50.3 | 2026-10-30 |
smollm3-3b@q6_k
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 46.8 | 33.0 | 19.2 | 73.2 | 56.2 | 38.5 | 2026-10-25 |
llama3.1:latest
AMD Radeon RX 6600/6600 XT/6600M |
8 GB | 5 | 46.0 | 52.9 | 28.9 | 58.6 | 55.5 | 40.9 | 2026-10-31 |
llama3.1:8b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 3 | 45.5 | 29.1 | 32.5 | 55.8 | 50.8 | 43.0 | 2026-10-31 |
mistralai/ministral-3-3b
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 5 | 45.5 | 11.0 | 27.6 | 46.6 | 60.4 | 47.5 | 2026-10-12 |
nvidia/nemotron-3-nano-4b
NVIDIA GeForce GTX 1050 |
2 GB | 3 | 41.9 | 4.9 | 12.7 | 43.6 | 72.5 | 38.6 | 2026-10-12 |
schematron-3b
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 39.6 | 37.8 | 8.3 | 59.7 | 56.6 | 33.8 | 2026-10-30 |
hermes-3-llama-3.1-8b
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 7 | 37.3 | 21.2 | 19.4 | 43.0 | 43.2 | 43.5 | 2026-10-17 |
smollm2-1.7b-instruct
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 35.8 | 49.4 | 19.8 | 40.9 | 49.2 | 33.3 | 2026-10-25 |
ternary-bonsai-2-2b
NVIDIA GeForce GTX 1050 |
2 GB | 4 | 35.3 | 39.1 | 12.2 | 39.7 | 58.6 | 30.5 | 2026-10-30 |
qwen2.5-coder:7b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 4 | 34.3 | 52.1 | 41.2 | 20.1 | 37.8 | 38.2 | 2026-10-31 |
llama-3.2-3b-instruct
NVIDIA GeForce RTX 2050 |
4 GB | 4 | 34.3 | 45.7 | 11.6 | 29.9 | 57.6 | 38.2 | 2026-10-20 |
theprint-12b-moe-3a-q4_k_m
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 33.4 | 34.1 | 11.7 | 30.0 | 51.1 | 41.0 | 2026-10-30 |
prism-ml/Ternary-Bonsai-2-2B-gguf:PQ2_0
NVIDIA GeForce RTX 4070 |
12 GB | 11 | 32.4 | 372.4 | 7.6 | 46.9 | 39.3 | 35.7 | 2026-10-16 |
allenai.OLMoE-1B-7B-0125-Instruct.Q5_K_M
NVIDIA GeForce RTX 4060 Laptop GPU |
8 GB | 10 | 31.4 | 185.1 | 8.3 | 40.5 | 53.5 | 23.1 | 2026-10-30 |
IFM/K2-Horizon-0.9B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 7 | 29.4 | 284.4 | 4.3 | 46.8 | 33.8 | 32.6 | 2026-10-15 |
qwen3.8-2b-distill
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 6 | 28.2 | 88.4 | 7.6 | 17.1 | 46.6 | 41.6 | 2026-10-13 |
phi-3.1-mini-4k-instruct
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 4 | 28.2 | 76.2 | 3.2 | 38.3 | 48.4 | 22.9 | 2026-10-14 |
smollm2-1.7b-instruct
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 25.3 | 123.3 | 7.8 | 17.1 | 47.3 | 29.1 | 2026-10-26 |
luciole-1b-instruct-1.1
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 21.6 | 61.7 | 0.0 | 31.3 | 37.4 | 17.6 | 2026-10-30 |
eurollm-1.7b-instruct
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 3 | 10.0 | 145.1 | 0.8 | 30.2 | 8.5 | 0.5 | 2026-10-12 |
qwen2.5-0.5b-instruct-q4_k_m
AMD Radeon RX 7900 XTX |
24 GB | 5 | 8.9 | 289.2 | 3.8 | 12.5 | 8.0 | 11.3 | 2026-10-20 |
qwen2.5-0.5b-nnl-distilled-clean-q4_k_m
AMD Radeon RX 7900 XTX |
24 GB | 3 | 6.7 | 346.3 | 3.4 | 10.1 | 7.7 | 5.5 | 2026-10-20 |
eurollm-1.7b
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 5 | 2.0 | 166.5 | 1.0 | 2.8 | 2.3 | 1.8 | 2026-10-12 |
ministral-3b-instruct
NVIDIA GeForce RTX 2050 |
4 GB | 6 | 1.7 | 49.3 | 0.1 | 3.7 | 1.9 | 1.2 | 2026-10-19 |
ministral-1b-base
NVIDIA GeForce RTX 3060 Laptop GPU |
6 GB | 7 | 0.6 | 183.6 | 0.0 | 2.4 | 0.0 | 0.0 | 2026-10-26 |