Running
1
llm-bench.io
📈
Live leaderboard of local LLMs — real-world quality & speed
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
llm-bench.io — Local LLM Leaderboard
Real-world benchmarks from actual users — LLM-judged quality and speed across coding, agent, role-play & research tasks, grouped by VRAM.
Run your own test →
| Model | VRAM | Runs | Quality | Speed (tok/s) | Coding | Agent | Role-Play | Research | Updated |
|---|---|---|---|---|---|---|---|---|---|
Qwen3.8-27B-MTPLX-Optimized-Quality
Apple M5 Max |
64 GB | 3 | 87.2 | 37.8 | 79.1 | 88.2 | 92.9 | 88.6 | 2026-09-25 |
mtplx-qwen38-27b-optimized-quality
Apple M5 Max |
128 GB | 3 | 87.2 | 35.0 | 78.4 | 90.6 | 92.4 | 87.6 | 2026-09-01 |
unsloth/Qwen3.8-27B-GGUF:IQ3_S
NVIDIA GeForce RTX 4090 |
23 GB | 4 | 86.9 | 108.6 | 83.3 | 86.2 | 90.3 | 87.9 | 2026-08-29 |
qwen3.8-27b-gsq-rco
AMD Radeon RX 9070/9070 XT/9070 GRE |
15 GB | 3 | 86.1 | 32.6 | 75.8 | 88.1 | 92.4 | 88.0 | 2026-09-15 |
unsloth/Qwen3.8-27B-GGUF
AMD Radeon RX 7900 XTX |
23 GB | 43 | 86.0 | 49.4 | 81.1 | 85.3 | 90.8 | 86.7 | 2026-09-25 |
mtplx-qwen38-27b-optimized-quality
Apple M4 Max |
64 GB | 3 | 85.7 | 35.5 | 77.7 | 85.2 | 93.1 | 86.7 | 2026-09-02 |
Dirk-Qwen3.8-27B-UD-IQ4_XS
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 85.5 | 37.5 | 79.2 | 87.2 | 88.0 | 87.8 | 2026-09-17 |
Tiel-Coder-35B-A3B-Q4_K_S
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 5 | 85.1 | 162.4 | 79.2 | 87.8 | 88.9 | 84.6 | 2026-09-19 |
unsloth/Qwen3.8-27B-GGUF:Q4_K_M
NVIDIA GeForce RTX 4090 |
23 GB | 6 | 85.1 | 95.3 | 78.0 | 85.9 | 89.0 | 87.4 | 2026-08-29 |
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 |
mtplx-flash-next-bare-speed
Apple M5 Max |
128 GB | 3 | 85.0 | 57.5 | 75.6 | 84.6 | 93.3 | 86.3 | 2026-09-01 |
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 |
Ornith-1.5-35B-A3B-oQ8e-mtp
Apple M5 Max |
64 GB | 4 | 84.9 | 98.5 | 76.8 | 87.9 | 88.9 | 86.0 | 2026-09-24 |
qwen3.8-27b-UD-Q4_K_XL
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 3 | 84.9 | 50.7 | 80.6 | 83.7 | 86.9 | 88.5 | 2026-09-08 |
Qwen3.8-27B-oQ6e-mtp
Apple M5 Max |
64 GB | 3 | 84.8 | 42.6 | 76.8 | 83.8 | 92.6 | 85.9 | 2026-09-24 |
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-oQ4e-mtp
Apple M5 Max |
64 GB | 21 | 84.0 | 46.2 | 76.4 | 82.6 | 91.4 | 85.8 | 2026-09-23 |
Qwen3.8-27B-GSQ-RCO-IQ3_S
NVIDIA GeForce RTX 4080 SUPER |
16 GB | 4 | 83.8 | 73.6 | 75.3 | 84.7 | 88.8 | 86.3 | 2026-09-04 |
Ornith-1.5-35B-A3B-oQ4e-mtp
Apple M4 Pro |
48 GB | 6 | 83.6 | 70.3 | 76.0 | 83.3 | 89.3 | 85.6 | 2026-09-22 |
K2-Horizon-MoVA-36B-A4B-MLX-4bit
Apple M5 Max |
64 GB | 3 | 83.6 | 48.5 | 82.5 | 90.8 | 76.1 | 84.9 | 2026-09-11 |
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 |
Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 7 | 83.3 | 103.5 | 76.1 | 88.3 | 84.1 | 84.5 | 2026-09-24 |
Qwen3.8-27B-oQ4e-mtp
Apple M4 Max |
128 GB | 70 | 83.3 | 44.9 | 77.0 | 81.4 | 88.9 | 85.9 | 2026-09-22 |
Qwen3.8-27B-UD-IQ3_S
NVIDIA GeForce RTX 4080 SUPER |
16 GB | 48 | 83.2 | 78.8 | 77.8 | 81.6 | 87.8 | 85.7 | 2026-09-05 |
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 |
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 |
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 |
Qwen3.8-Flash-Next-oQ5e-mtp
Apple M4 Max |
128 GB | 100 | 82.9 | 54.5 | 74.5 | 83.2 | 89.6 | 84.3 | 2026-09-23 |
| 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 | 54 | 82.9 | 34.0 | 78.4 | 78.5 | 88.9 | 85.8 | 2026-09-23 |
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 |
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 | |
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-Flash-Next-oQ4e-mtp
Apple M4 Max |
128 GB | 95 | 81.8 | 58.6 | 72.6 | 82.9 | 87.5 | 84.4 | 2026-09-27 |
Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 81.7 | 108.1 | 77.3 | 80.5 | 83.7 | 85.4 | 2026-09-11 |
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 |
Qwen3.8-27B-oQ8e-mtp
Apple M5 Max |
64 GB | 22 | 81.6 | 34.1 | 72.0 | 82.0 | 88.1 | 84.2 | 2026-09-26 |
Qwen3.8-27B-Q4_K_XL
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 15 | 81.5 | 72.4 | 78.7 | 76.5 | 85.7 | 85.0 | 2026-09-05 |
| 128 GB | 3 | 81.3 | 59.5 | 69.3 | 84.2 | 91.5 | 80.0 | 2026-09-12 | |
| 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/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL
NVIDIA GeForce RTX 3080 Ti + NVIDIA GeForce RTX 3080 |
20 GB | 3 | 80.8 | 180.6 | 74.1 | 85.8 | 83.6 | 79.9 | 2026-09-14 |
Ornith-1.5-35B-A3B-IQ4_XS
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 3 | 80.7 | 139.5 | 78.7 | 81.4 | 82.4 | 80.2 | 2026-09-05 |
Unsloth-Ornith-1.5-35B-A3B-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 6 | 80.7 | 88.2 | 76.9 | 73.6 | 89.0 | 83.3 | 2026-09-25 |
Qwen3.8-27B-oQ8e-fp16-mtp
Apple M2 Ultra |
128 GB | 13 | 80.7 | 34.1 | 72.7 | 77.3 | 88.2 | 84.6 | 2026-09-04 |
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 |
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 |
qwen38-27b
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 6 | 79.6 | 72.7 | 67.5 | 77.3 | 88.7 | 85.0 | 2026-09-08 |
Qwen3.8-27B-UD-Q6_K_XL
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition |
96 GB | 4 | 79.5 | 84.3 | 75.9 | 76.9 | 84.4 | 80.6 | 2026-08-31 |
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 |
Qwen3.8-27B-UD-Q3_K_XL
NVIDIA GeForce RTX 5070 Ti |
15 GB | 10 | 79.1 | 62.5 | 59.0 | 87.3 | 92.2 | 78.1 | 2026-09-18 |
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 |
16 GB | 4 | 78.9 | 26.8 | 77.2 | 81.8 | 80.9 | 75.8 | 2026-09-01 |
Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 78.8 | 116.1 | 75.0 | 71.5 | 84.3 | 84.2 | 2026-09-23 |
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 |
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 |
nail-qwen3.6-35b-a3b
AMD Radeon RX 9050 / 9060 XT |
15 GB | 5 | 77.2 | 73.1 | 72.1 | 78.7 | 82.8 | 75.2 | 2026-09-22 |
Qwen3.8-27B-Q8_0
AMD Radeon RX 7900 XT/7900 XTX/7900M |
23 GB | 22 | 76.8 | 59.6 | 71.7 | 75.8 | 82.0 | 77.8 | 2026-09-16 |
Qwen3.6-35B-A3B-IQ4_NL
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 17 | 75.9 | 164.8 | 67.1 | 74.7 | 83.0 | 78.7 | 2026-09-05 |
gpt-oss-20b-UD-Q8_K_XL
NVIDIA GeForce RTX 5060 |
8 GB | 3 | 75.6 | 148.4 | 70.3 | 83.8 | 71.6 | 76.7 | 2026-09-09 |
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 |
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 |
Ornith-1.5-9B-Q6_K
NVIDIA GeForce RTX 5060 |
8 GB | 4 | 73.4 | 57.6 | 70.8 | 54.8 | 84.1 | 83.9 | 2026-09-23 |
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 |
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 |
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 |
gemma-4-26b-a4b-q4kxl
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
23 GB | 3 | 69.5 | 169.9 | 67.9 | 75.2 | 79.8 | 55.2 | 2026-09-05 |
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 |
qwen3.5-9b-mtp@q8_0
AMD Radeon RX 7600 XT |
15 GB | 3 | 67.5 | 41.8 | 56.2 | 62.6 | 80.5 | 70.7 | 2026-09-11 |
mudler/Qwen3.6-35B-A3B-APEX-MTP-GGUF
Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 |
16 GB | 4 | 66.8 | 31.6 | 65.6 | 59.9 | 68.0 | 73.8 | 2026-09-01 |
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 |
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 XT/7900 XTX/7900M |
23 GB | 4 | 58.9 | 51.8 | 26.6 | 83.6 | 85.1 | 40.1 | 2026-09-14 |
Ling-3.0-tiny-oQ8e
Apple M4 Max |
128 GB | 3 | 58.7 | 126.0 | 45.2 | 68.2 | 43.6 | 77.5 | 2026-09-10 |
| 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 |
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 |
Ornith-1.5-35B-Q8_0
AMD Radeon RX 7900 XT/7900 XTX/7900M |
23 GB | 7 | 49.9 | 73.1 | 46.9 | 51.6 | 52.0 | 49.2 | 2026-09-15 |
ling-oq4e
Apple M1 |
16 GB | 4 | 46.1 | 47.6 | 6.2 | 64.1 | 59.5 | 54.8 | 2026-09-12 |
unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 44.1 | 92.8 | 11.8 | 61.1 | 51.5 | 52.0 | 2026-09-18 |
ling-oq8e
Apple M1 |
16 GB | 6 | 44.0 | 33.8 | 6.0 | 73.7 | 45.3 | 51.1 | 2026-09-12 |
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/Qwen3.5-0.8B-MTP-GGUF
NVIDIA GeForce RTX 4070 |
11 GB | 3 | 24.1 | 239.4 | 12.2 | 28.6 | 32.8 | 22.9 | 2026-09-26 |
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 |
Qwen3.8-27B-oQ2e-mtp
Apple M5 Max |
64 GB | 3 | 10.3 | 44.0 | 0.0 | 28.0 | 7.7 | 5.6 | 2026-08-30 |
models 0
None public yet