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 |
|---|---|---|---|---|---|---|---|---|---|
unsloth/Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
23 GB | 29 | 87.0 | 44.8 | 81.7 | 87.1 | 91.7 | 87.6 | 2026-09-25 |
Qwen3.8-27B-MTPLX-Optimized-Quality
Apple M5 Max |
64 GB | 4 | 85.9 | 39.4 | 79.3 | 86.2 | 91.6 | 86.5 | 2026-09-27 |
ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Swift-1.5-Qwen3.8-27B-Q4_K_S
AMD Radeon RX 7900 XTX + Advanced Micro Devices, Inc. [AMD/ATI] Raphael |
24 GB | 3 | 85.8 | 72.4 | 82.3 | 81.9 | 90.4 | 88.7 | 2026-10-05 |
Hemmingway-1-oQ8e-mtp
Apple M5 Max |
64 GB | 4 | 85.4 | 28.2 | 76.0 | 85.0 | 93.2 | 87.3 | 2026-09-29 |
hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S
AMD Radeon RX 7900 XTX |
23 GB | 3 | 85.3 | 27.6 | 78.0 | 85.1 | 92.9 | 85.4 | 2026-09-27 |
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed
NVIDIA GeForce RTX 5080 |
16 GB | 6 | 85.2 | 49.4 | 79.2 | 84.8 | 88.8 | 87.9 | 2026-10-10 |
Swift-1.5-Qwen3.8-27b-oQ8e-mtp
Apple M5 Max |
64 GB | 5 | 85.2 | 31.3 | 79.9 | 85.8 | 89.5 | 85.6 | 2026-09-29 |
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 |
ukisai/Swift-Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
23 GB | 6 | 85.1 | 33.4 | 77.2 | 86.5 | 88.8 | 87.7 | 2026-09-24 |
bottlecapai/ThinkingCap-Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
23 GB | 5 | 85.0 | 37.8 | 80.9 | 82.0 | 92.0 | 85.1 | 2026-09-24 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp
AMD Radeon RX 7800 XT |
16 GB | 10 | 84.9 | 48.9 | 77.1 | 83.0 | 93.5 | 85.7 | 2026-10-09 |
Ornith-1.5-35B-A3B-oQ8e-mtp
Apple M5 Max |
64 GB | 5 | 84.8 | 116.6 | 79.8 | 87.6 | 87.0 | 84.6 | 2026-10-10 |
Swift-Qwen3.8-27b-oQ4e-fp16-mtp
Apple M5 Max |
64 GB | 3 | 84.7 | 41.5 | 77.0 | 85.9 | 90.4 | 85.4 | 2026-09-24 |
Qwen3.8-27B-YMQ-M-TI
NVIDIA GeForce RTX 5060 |
8 GB | 6 | 84.6 | 36.0 | 78.1 | 85.0 | 89.2 | 86.3 | 2026-10-05 |
unsloth/Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
24 GB | 21 | 84.5 | 54.0 | 79.8 | 82.9 | 90.1 | 85.2 | 2026-09-30 |
Qwen3.8-27B-oQ6e-mtp
Apple M5 Max |
64 GB | 6 | 84.3 | 50.2 | 81.3 | 81.9 | 88.6 | 85.5 | 2026-10-10 |
Qwen3.8-27B-oQ8e-mtp
Apple M5 Max |
64 GB | 10 | 84.3 | 38.8 | 75.9 | 84.9 | 88.6 | 87.8 | 2026-10-10 |
Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 17 | 84.2 | 84.1 | 77.1 | 87.7 | 86.3 | 85.8 | 2026-10-05 |
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-Flash-Next-Sushi-2.6bpw
Apple M5 Max |
64 GB | 3 | 84.1 | 73.2 | 79.3 | 83.1 | 89.6 | 84.4 | 2026-10-01 |
swift-1.5-iq3_xxs
AMD Radeon RX 7900 XTX + Advanced Micro Devices, Inc. [AMD/ATI] Raphael |
24 GB | 5 | 84.0 | 53.1 | 78.1 | 84.8 | 88.5 | 84.7 | 2026-10-03 |
Nex-N2.5-mini-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 83.9 | 80.3 | 84.5 | 88.5 | 81.5 | 80.9 | 2026-10-01 |
swift-1.5-qwen3.8-27b-uncensored
NVIDIA GeForce RTX 5060 Ti + NVIDIA GeForce RTX 5090 |
31 GB | 12 | 83.8 | 277.4 | 77.3 | 84.1 | 89.8 | 84.0 | 2026-10-08 |
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 |
Ornith-1.5-35B-A3B-GSQ-RCO-3bit
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 83.5 | 94.2 | 75.8 | 86.1 | 86.8 | 85.3 | 2026-10-04 |
Nex-N2.5-mini-mixed-Q2Q3-vision-trial
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 83.4 | 97.3 | 77.5 | 81.6 | 88.7 | 85.9 | 2026-09-30 |
Ornith-1.5-35B-A3B-oQ6e-mtp
Apple M4 Pro |
48 GB | 3 | 83.4 | 59.2 | 76.5 | 88.2 | 86.4 | 82.7 | 2026-09-15 |
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 |
Qwen3.8-27B-oQ4e-mtp
Apple M4 Max |
128 GB | 69 | 83.3 | 45.0 | 77.0 | 81.3 | 88.9 | 85.9 | 2026-09-22 |
ornith-ai/Ornith-1.5-35B-A3B-GGUF
AMD Radeon RX 7900 XTX |
24 GB | 4 | 83.2 | 90.8 | 83.8 | 72.4 | 90.3 | 86.1 | 2026-09-30 |
dirk-qwen3.8-27b@iq3_xxs
AMD Radeon RX 9070/9070 XT/9070 GRE |
15 GB | 3 | 83.2 | 18.8 | 74.5 | 87.1 | 84.9 | 86.3 | 2026-09-14 |
Ornith-1.5-35B-A3B-oQ4e-mtp
Apple M4 Pro |
48 GB | 7 | 83.1 | 70.7 | 76.9 | 81.2 | 88.8 | 85.4 | 2026-09-29 |
Qwen3.8-27B-oQ4e-mtp
Apple M5 Max |
64 GB | 16 | 83.1 | 41.8 | 76.2 | 82.9 | 89.7 | 83.7 | 2026-10-10 |
Qwen3.8-27B-oQ6e-mtp
Apple M4 Max |
128 GB | 26 | 83.1 | 38.6 | 77.6 | 77.9 | 90.4 | 86.3 | 2026-09-24 |
Nex-N2.5-mini-IQ3_XXS
AMD Radeon RX 7800 XT |
16 GB | 3 | 83.0 | 102.4 | 78.6 | 87.3 | 85.0 | 81.0 | 2026-10-05 |
Qwen3.8Next
Apple M5 Max |
128 GB | 4 | 83.0 | 54.7 | 74.7 | 84.7 | 89.4 | 83.2 | 2026-09-26 |
qwen3
AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT + AMD Radeon RX 6800/6800 XT / 6900 XT |
15 GB | 3 | 83.0 | 35.7 | 73.7 | 82.8 | 92.1 | 83.5 | 2026-09-25 |
| 128 GB | 3 | 82.9 | 51.8 | 76.6 | 84.1 | 86.2 | 84.7 | 2026-09-12 | |
Qwen3.8-27B-oQ8e-mtp
Apple M4 Max |
128 GB | 65 | 82.9 | 34.2 | 78.2 | 77.8 | 89.5 | 86.2 | 2026-09-27 |
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 |
Qwen3.8-Flash-Next-oQ5e-mtp
Apple M4 Max |
128 GB | 90 | 82.7 | 56.4 | 74.3 | 83.0 | 89.5 | 84.1 | 2026-09-23 |
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 |
Qwen3.8-Flash-Next-REAP-384-oQ5e-BF16-MTP-PLE
Apple M4 Max |
128 GB | 23 | 82.6 | 61.1 | 74.6 | 83.1 | 88.9 | 83.8 | 2026-09-22 |
HermesFableAgentThink
Apple M5 Max |
128 GB | 3 | 82.6 | 19.2 | 68.2 | 86.3 | 93.1 | 82.7 | 2026-09-27 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp
AMD Radeon RX 7800 XT |
16 GB | 4 | 82.4 | 39.6 | 79.0 | 83.8 | 81.5 | 85.5 | 2026-10-06 |
qwen3.8:27b-q4_K_M
AMD Radeon RX 7800 XT |
16 GB | 4 | 82.4 | 26.7 | 77.3 | 77.4 | 92.0 | 83.0 | 2026-10-11 |
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S
NVIDIA GeForce RTX 5070 Ti |
16 GB | 4 | 82.3 | 48.6 | 65.9 | 85.7 | 91.1 | 86.3 | 2026-09-15 |
| 128 GB | 14 | 82.1 | 47.8 | 62.2 | 89.3 | 90.3 | 86.6 | 2026-09-13 | |
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 |
Qwen3.8-Flash-Next-oQ4e-mtp-BF16PLE-v1
Apple M4 Max |
128 GB | 21 | 81.9 | 53.8 | 65.0 | 83.4 | 90.3 | 88.9 | 2026-09-13 |
qwen3.8-27b-splash
Apple M5 Max |
64 GB | 11 | 81.7 | 73.4 | 73.1 | 79.8 | 89.7 | 84.1 | 2026-10-10 |
Qwen3.8-Flash-Next-oQ4e-mtp
Apple M4 Max |
128 GB | 73 | 81.7 | 64.0 | 72.6 | 82.7 | 87.4 | 84.2 | 2026-09-27 |
unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL
Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 |
32 GB | 3 | 81.7 | 34.3 | 72.2 | 84.9 | 84.3 | 85.2 | 2026-10-04 |
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 |
Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL
Tesla P100-PCIE-16GB |
16 GB | 14 | 81.6 | 39.1 | 76.6 | 83.8 | 84.0 | 81.8 | 2026-09-22 |
muse-glimmer:30b-q4_K_M
AMD Radeon RX 7800 XT |
16 GB | 3 | 81.5 | 27.8 | 69.0 | 90.6 | 84.7 | 81.5 | 2026-10-11 |
Qwen3.8-Flash-Next-oQ4e-mtp
Apple M5 Max |
64 GB | 4 | 81.4 | 24.6 | 57.3 | 85.4 | 95.8 | 87.3 | 2026-10-06 |
Cyber-Tiel-Coder-35B-A3B.APEX-I-NanoPlus
AMD Radeon RX 7900 XTX |
24 GB | 6 | 81.3 | 113.1 | 78.9 | 81.6 | 82.3 | 82.4 | 2026-10-02 |
| 128 GB | 3 | 81.3 | 59.5 | 69.3 | 84.2 | 91.5 | 80.0 | 2026-09-12 | |
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 |
cyber-tiel-coder-35b-a3b-mtp
AMD Radeon RX 7900 XTX |
24 GB | 9 | 81.1 | 115.9 | 69.6 | 86.4 | 85.9 | 82.5 | 2026-10-01 |
| 128 GB | 4 | 81.1 | 63.8 | 70.3 | 85.2 | 87.0 | 82.0 | 2026-09-12 | |
Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS
Tesla P100-PCIE-16GB |
16 GB | 41 | 80.9 | 60.2 | 76.5 | 82.9 | 82.4 | 81.8 | 2026-09-23 |
Unsloth-Ornith-1.5-35B-A3B-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 7 | 80.7 | 88.4 | 76.7 | 75.0 | 88.6 | 82.6 | 2026-09-28 |
Nex-N2.5-mini-MLX-4bit
Apple M5 Max |
64 GB | 20 | 80.3 | 137.0 | 73.9 | 81.2 | 81.1 | 85.1 | 2026-09-12 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 79.8 | 39.2 | 62.1 | 81.9 | 93.6 | 81.7 | 2026-09-28 |
Qwen3.8-Flash-Next-Dynamic-oQ5e-BF16-PLE-mtp
Apple M4 Max |
128 GB | 4 | 79.7 | 52.4 | 62.7 | 83.4 | 88.5 | 84.0 | 2026-09-14 |
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 |
Qwen3.8-27B-Q4_K_S
AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT + AMD Radeon RX 6800/6800 XT / 6900 XT |
15 GB | 3 | 79.5 | 36.1 | 69.2 | 77.9 | 85.7 | 85.2 | 2026-09-25 |
Jundot/Qwen3.8-27B-oQ6e-mtp
Apple M5 Max |
64 GB | 4 | 78.8 | 60.5 | 63.0 | 80.1 | 88.1 | 84.1 | 2026-10-02 |
unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL
Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 |
32 GB | 5 | 78.7 | 34.6 | 52.2 | 87.0 | 89.5 | 86.2 | 2026-10-10 |
Ornith-1.5-35B-A3B-Q5_K_M
Tesla P100-PCIE-16GB |
16 GB | 3 | 78.4 | 33.4 | 71.9 | 82.8 | 83.3 | 75.5 | 2026-09-21 |
tiel-coder-35b-a3b-mtp
AMD Radeon RX 9050 / 9060 XT |
15 GB | 6 | 78.3 | 76.5 | 65.5 | 82.1 | 83.0 | 82.5 | 2026-09-22 |
ukisai/Swift-1.5-Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
24 GB | 3 | 78.1 | 55.3 | 52.4 | 87.3 | 88.0 | 84.8 | 2026-09-28 |
Qwen3.8-35B-A3B-Distill.Q4_K_M
Tesla P100-PCIE-16GB |
16 GB | 3 | 77.8 | 41.2 | 69.8 | 77.3 | 89.1 | 74.9 | 2026-09-21 |
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 |
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 |
nail-qwen3.6-35b-a3b
AMD Radeon RX 9050 / 9060 XT |
15 GB | 4 | 77.4 | 51.0 | 71.5 | 79.7 | 83.0 | 75.1 | 2026-09-22 |
Ornith-1.5-9B-Q6_K
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 76.9 | 60.0 | 74.0 | 65.5 | 84.2 | 83.9 | 2026-09-23 |
Qwen3.8-27B-Q8_0
AMD Radeon RX 7900 XTX |
24 GB | 22 | 76.8 | 59.6 | 71.7 | 75.8 | 82.0 | 77.8 | 2026-09-16 |
Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 76.6 | 105.8 | 62.0 | 77.6 | 82.8 | 83.8 | 2026-09-28 |
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 |
ornith-1.5-9b
NVIDIA GeForce RTX 5080 |
16 GB | 3 | 75.7 | 124.8 | 71.3 | 66.6 | 83.3 | 81.5 | 2026-10-11 |
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 |
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 |
unsloth/Ornith-1.0-9B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 74.7 | 62.2 | 61.5 | 80.4 | 78.6 | 78.4 | 2026-09-26 |
gemma-4-26B-A4B-it-UD-IQ4_NL
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 74.5 | 83.2 | 67.6 | 82.5 | 80.5 | 67.5 | 2026-09-12 |
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 |
Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS
Tesla P100-PCIE-16GB |
16 GB | 3 | 74.3 | 38.3 | 61.6 | 75.4 | 81.6 | 78.8 | 2026-09-22 |
Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 74.0 | 54.7 | 62.8 | 62.9 | 88.1 | 82.3 | 2026-10-01 |
Tiel-Coder-35B-A3B-UD-IQ3_XXS
Tesla P100-PCIE-16GB |
16 GB | 3 | 72.6 | 57.2 | 67.1 | 73.1 | 73.5 | 76.5 | 2026-09-21 |
Qwen3.8-27B-UD-Q3_K_XL
NVIDIA GeForce RTX 5070 Ti |
16 GB | 10 | 71.5 | 63.2 | 33.4 | 84.4 | 90.0 | 78.3 | 2026-10-03 |
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-4-12B-it-qat-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 4 | 70.9 | 58.5 | 61.3 | 69.6 | 81.8 | 70.8 | 2026-09-27 |
gemma4:12b-it-qat
AMD Radeon RX 7800 XT |
15 GB | 3 | 70.9 | 47.3 | 65.0 | 74.4 | 75.5 | 68.8 | 2026-09-21 |
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 |
ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit
Apple M4 Max |
128 GB | 3 | 70.6 | 71.5 | 52.5 | 72.1 | 79.0 | 78.9 | 2026-09-18 |
unsloth/Qwen3.5-9B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 8 | 68.5 | 92.1 | 56.1 | 67.8 | 78.7 | 71.6 | 2026-09-27 |
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 |
ornith-ai/Ornith-1.5-9B-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 5 | 67.6 | 63.7 | 46.6 | 58.0 | 83.4 | 82.5 | 2026-10-06 |
prism-ml/Ternary-Bonsai-2-27B-gguf
NVIDIA GeForce RTX 4070 |
11 GB | 7 | 67.3 | 48.6 | 40.4 | 82.2 | 83.4 | 63.5 | 2026-09-27 |
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 |
occamy-1.0.i1-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 66.6 | 78.2 | 28.7 | 64.1 | 89.4 | 84.4 | 2026-09-30 |
unsloth/Qwen3.5-4B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 13 | 66.2 | 114.6 | 56.0 | 62.2 | 75.1 | 71.6 | 2026-10-07 |
apodex_Apodex-1.1-mini-IQ2_M
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 65.9 | 94.3 | 58.8 | 55.2 | 76.7 | 72.8 | 2026-10-01 |
hf.co/unsloth/gemma-4-E4B-it-qat-GGUF:UD-Q4_K_XL
NVIDIA GeForce RTX 2070 SUPER |
8 GB | 4 | 64.8 | 79.7 | 52.9 | 74.1 | 71.5 | 60.8 | 2026-09-29 |
ornith-ai/Ornith-1.5-9B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 64.7 | 66.4 | 28.1 | 66.7 | 78.4 | 85.6 | 2026-09-28 |
Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL
Tesla P100-PCIE-16GB |
16 GB | 3 | 63.4 | 38.5 | 73.7 | 74.5 | 35.8 | 69.6 | 2026-09-21 |
google/gemma-4-e2b
Intel(R) Arc(TM) Pro 140T GPU (16GB) + NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU |
5 GB | 3 | 63.2 | 46.7 | 43.5 | 67.0 | 75.5 | 66.6 | 2026-09-22 |
unsloth/Qwen3.5-4B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 7 | 61.2 | 110.0 | 52.4 | 52.8 | 73.4 | 66.2 | 2026-09-28 |
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 |
Qwen3.8-9B-Distill-uncensored-heretic.i1-IQ3_M
Tesla P100-PCIE-16GB |
16 GB | 3 | 59.7 | 34.3 | 36.3 | 68.5 | 69.6 | 64.5 | 2026-09-21 |
qwen3.8 27b
AMD Radeon RX 7900 XTX |
24 GB | 4 | 58.9 | 51.8 | 26.6 | 83.6 | 85.1 | 40.1 | 2026-09-14 |
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 |
| 128 GB | 3 | 54.0 | 77.4 | 7.6 | 61.5 | 78.8 | 68.2 | 2026-09-20 | |
unsloth/Qwen3.8-27B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 8 | 54.0 | 40.1 | 8.1 | 71.2 | 81.1 | 55.4 | 2026-09-27 |
qwen3:14b
NVIDIA GeForce RTX 5060 Ti |
16 GB | 3 | 53.4 | 189.2 | 6.7 | 69.1 | 74.9 | 62.9 | 2026-10-01 |
LFM2.5-8B-A1B-Q4_K_M
NVIDIA GeForce RTX 4070 |
11 GB | 4 | 50.4 | 281.2 | 9.1 | 72.6 | 70.9 | 48.8 | 2026-09-18 |
unsloth/LFM2.5-8B-A1B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 50.0 | 246.9 | 16.9 | 67.3 | 68.0 | 48.0 | 2026-09-28 |
Ornith-1.5-35B-Q8_0
AMD Radeon RX 7900 XTX |
24 GB | 7 | 49.9 | 73.1 | 46.9 | 51.6 | 52.0 | 49.2 | 2026-09-15 |
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 |
ling-oq4e
Apple M1 |
16 GB | 4 | 46.1 | 47.6 | 6.2 | 64.1 | 59.5 | 54.8 | 2026-09-12 |
ling-oq8e
Apple M1 |
16 GB | 6 | 44.0 | 33.8 | 6.0 | 73.7 | 45.3 | 51.1 | 2026-09-12 |
unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 4 | 42.9 | 93.4 | 11.6 | 52.4 | 55.5 | 52.2 | 2026-09-27 |
unsloth/Qwen3.5-2B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 8 | 42.8 | 163.6 | 37.0 | 47.3 | 56.3 | 30.7 | 2026-09-28 |
bartowski/MiniCPM5-2B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 4 | 42.5 | 171.2 | 10.9 | 50.1 | 43.3 | 65.8 | 2026-09-28 |
unsloth/LFM2.5-1.2B-Instruct-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 6 | 35.5 | 350.9 | 6.8 | 61.6 | 51.7 | 21.9 | 2026-09-26 |
unsloth/LFM2.5-1.2B-Thinking-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 8 | 31.2 | 321.5 | 7.4 | 43.7 | 48.3 | 25.3 | 2026-09-26 |
unsloth/gemma-4-E4B-it-qat-mobile-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 27.4 | 74.6 | 11.2 | 32.4 | 41.4 | 24.6 | 2026-09-27 |
unsloth/LFM2.5-VL-1.6B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 20.6 | 848.6 | 4.3 | 11.7 | 39.1 | 27.1 | 2026-09-26 |
unsloth/Qwen3.5-0.8B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 5 | 19.6 | 341.9 | 11.4 | 28.1 | 21.7 | 17.1 | 2026-09-27 |