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-UD-IQ3_S
NVIDIA GeForce RTX 4090 |
24 GB | 3 | 88.2 | 84.1 | 82.1 | 89.0 | 92.5 | 89.0 | 2026-11-02 |
JonathanColetti-Qwen3.8-27B-Uncensored-GGUF-Q5_K_M
NVIDIA RTX A6000 |
47 GB | 3 | 87.8 | 37.1 | 84.4 | 86.6 | 92.4 | 87.7 | 2026-11-02 |
qwen3.8-27b-turbo
AMD Radeon AI PRO R9700 |
32 GB | 10 | 87.5 | 133.7 | 81.5 | 88.7 | 93.8 | 85.8 | 2026-11-15 |
Qwen3.8-27B
NVIDIA GeForce RTX 3090 |
24 GB | 13 | 87.5 | 44.6 | 81.0 | 88.8 | 92.0 | 88.4 | 2026-11-13 |
swift-1.5-27b-full
AMD Radeon AI PRO R9700 |
32 GB | 3 | 87.4 | 157.4 | 84.9 | 87.4 | 89.2 | 88.0 | 2026-11-15 |
ornith-1.5-35b-apex
AMD Radeon AI PRO R9700 |
32 GB | 5 | 87.3 | 146.0 | 83.6 | 90.1 | 87.7 | 87.6 | 2026-11-15 |
qwen3.8-27b-full
AMD Radeon AI PRO R9700 |
32 GB | 3 | 87.2 | 128.1 | 77.5 | 90.9 | 92.8 | 87.7 | 2026-11-15 |
qwen3.8-27b
AMD Radeon AI PRO R9700 |
32 GB | 5 | 87.2 | 77.4 | 78.9 | 88.7 | 92.2 | 88.9 | 2026-11-14 |
swift-1.5-27b
AMD Radeon AI PRO R9700 |
32 GB | 3 | 87.1 | 98.7 | 84.8 | 85.0 | 91.1 | 87.5 | 2026-11-14 |
ornith-1.5-35b-a3b-apex-i-quality
NVIDIA GeForce RTX 3070 Ti |
8 GB | 3 | 86.8 | 59.4 | 82.8 | 88.4 | 89.2 | 86.8 | 2026-11-11 |
Qwen3.8-Flash-Next-oQ3.5e-mtp
Apple M5 Ultra |
96 GB | 5 | 86.7 | 95.2 | 76.3 | 90.1 | 92.5 | 88.0 | 2026-11-13 |
swift-1.5-27b-turbo
AMD Radeon AI PRO R9700 |
32 GB | 3 | 86.6 | 158.2 | 80.6 | 87.7 | 89.7 | 88.6 | 2026-11-14 |
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 |
ornith-1.5-35b-a3b-apex-mtp-quality
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 86.5 | 103.2 | 79.9 | 88.5 | 90.3 | 87.3 | 2026-11-15 |
qwen3.8-flash-next-coder-iq1_m
NVIDIA GeForce RTX 3090 |
24 GB | 3 | 86.5 | 80.1 | 77.4 | 89.5 | 89.7 | 89.3 | 2026-11-12 |
| 47 GB | 3 | 86.5 | 26.5 | 82.7 | 85.8 | 92.2 | 85.4 | 2026-11-05 | |
qwen3.8-flash-next-ud-iq4_xs-v31-q8-engram
NVIDIA GeForce RTX 4090 |
24 GB | 13 | 86.3 | 82.6 | 73.8 | 91.6 | 92.6 | 87.2 | 2026-11-08 |
flash-next
AMD Radeon AI PRO R9700 |
32 GB | 3 | 86.1 | 81.0 | 74.1 | 86.6 | 95.0 | 88.7 | 2026-11-14 |
qwen3.8-27b-long
AMD Radeon AI PRO R9700 |
32 GB | 3 | 86.0 | 77.8 | 81.7 | 84.4 | 90.9 | 87.0 | 2026-11-14 |
cyber-tiel-coder-35b-a3b-mtp-ud-q5_k_xl
NVIDIA GeForce RTX 4070 |
12 GB | 5 | 85.8 | 102.8 | 82.0 | 89.8 | 86.9 | 84.6 | 2026-11-15 |
| 47 GB | 4 | 85.8 | 27.3 | 81.5 | 85.4 | 90.0 | 86.2 | 2026-11-04 | |
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 |
Ornith-1.5-35B-A3B.APEX-I-NanoPlus
NVIDIA GeForce GTX 1650 |
4 GB | 3 | 85.7 | 24.8 | 80.2 | 85.7 | 90.2 | 86.9 | 2026-11-06 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp
AMD Radeon RX 7800 XT |
16 GB | 6 | 85.6 | 43.6 | 80.3 | 86.1 | 86.9 | 89.0 | 2026-11-11 |
mlx-community/Qwen3.8-27B-4bit
Apple M5 Max |
64 GB | 6 | 85.4 | 85.3 | 76.9 | 86.0 | 91.2 | 87.4 | 2026-11-14 |
logicbeat/qwen3.8-27B_GSQ_RCO:latest
AMD Radeon RX 7600 XT |
16 GB | 6 | 85.4 | 23.0 | 82.1 | 81.4 | 90.5 | 87.6 | 2026-11-08 |
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-flash-next-iq3_s-fp8-ple
NVIDIA GeForce RTX 4090 |
24 GB | 7 | 85.2 | 99.8 | 69.7 | 89.9 | 92.0 | 89.0 | 2026-11-08 |
Swift-1.5-Uncensored
Tesla V100-PCIE-32GB |
32 GB | 6 | 85.1 | 59.6 | 79.3 | 83.4 | 91.7 | 85.8 | 2026-11-09 |
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp
AMD Radeon RX 7800 XT |
16 GB | 6 | 85.0 | 44.0 | 72.3 | 89.0 | 93.1 | 85.5 | 2026-11-08 |
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 |
Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF-RVN-Q5_K_M-mtp
NVIDIA RTX A6000 |
47 GB | 4 | 84.7 | 29.8 | 77.4 | 84.9 | 90.5 | 85.9 | 2026-11-04 |
GRM-3.2-Sky
Tesla V100-PCIE-32GB |
32 GB | 4 | 84.6 | 98.0 | 78.5 | 89.3 | 87.9 | 82.6 | 2026-11-09 |
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 |
strata_swift
AMD Radeon RX 7900 XTX |
24 GB | 4 | 84.4 | 56.4 | 64.8 | 91.8 | 92.6 | 88.3 | 2026-11-05 |
Cyber-Tiel
Tesla V100-PCIE-32GB |
32 GB | 5 | 84.3 | 100.7 | 77.6 | 89.6 | 84.8 | 85.3 | 2026-11-09 |
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp-ASCII-Condensed
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 84.3 | 38.8 | 68.6 | 88.3 | 93.0 | 87.3 | 2026-10-27 |
Qwen3.8-27B-GSQ-RCO-Intel-Arc-Tuned-MTP-3.2BPW
Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 |
32 GB | 3 | 84.3 | 18.9 | 63.2 | 92.2 | 93.5 | 88.5 | 2026-11-15 |
qwen3.8-flash-next-unsloth-ud-iq4_xs
NVIDIA GeForce RTX 3080 |
20 GB | 3 | 84.2 | 85.1 | 77.2 | 80.2 | 90.8 | 88.5 | 2026-11-09 |
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 |
iq3_s
NVIDIA GeForce RTX 3090 |
24 GB | 18 | 84.1 | 58.3 | 66.8 | 90.0 | 93.1 | 86.6 | 2026-11-10 |
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
NVIDIA GeForce RTX 3070 Ti |
8 GB | 3 | 84.0 | 25.1 | 80.3 | 83.3 | 89.2 | 83.0 | 2026-11-11 |
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-flash-next-unsloth-ud-q4_k_xl
AMD Radeon RX 7900 XTX |
24 GB | 23 | 83.6 | 50.0 | 68.5 | 89.4 | 89.6 | 87.1 | 2026-11-15 |
qwen3.8-large-ctx:latest
AMD Radeon RX 7600 XT |
16 GB | 3 | 83.6 | 23.6 | 83.5 | 83.7 | 82.9 | 84.1 | 2026-11-08 |
qwen3.8-flash-next-iq2_xs
AMD Radeon RX 7900 XT |
20 GB | 6 | 83.5 | 73.4 | 76.9 | 84.0 | 89.1 | 83.9 | 2026-11-13 |
Muse-Glimmer-30B-4bit
Apple M5 Max |
64 GB | 3 | 83.5 | 30.9 | 75.5 | 88.4 | 84.5 | 85.6 | 2026-11-14 |
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 |
qwen3.8-flash-next-iq3_xxs
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 5 | 83.1 | 51.1 | 68.0 | 87.0 | 91.1 | 86.5 | 2026-11-05 |
Cyber-Tiel-Coder-35B-A3B.APEX-I-NanoPlus
NVIDIA GeForce GTX 1650 |
4 GB | 3 | 83.1 | 24.1 | 76.2 | 85.8 | 85.2 | 85.2 | 2026-11-04 |
Qwen3.8-27B-oQ8e-mtp
Apple M5 Max |
64 GB | 27 | 82.9 | 47.1 | 74.3 | 84.8 | 88.3 | 84.1 | 2026-10-27 |
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 |
Qwen3.8-27B-oQ4e-mtp
Apple M4 Pro |
48 GB | 4 | 82.4 | 33.3 | 77.3 | 78.6 | 88.6 | 84.9 | 2026-10-20 |
Swift-Qwen3.8-27B-GGUF-Q6_K
NVIDIA RTX A6000 |
47 GB | 3 | 82.3 | 24.8 | 73.2 | 84.9 | 88.1 | 82.9 | 2026-11-04 |
unsloth/Qwen3.8-27B-GGUF
AMD RX 9060 XT |
16 GB | 3 | 82.2 | 22.2 | 76.0 | 83.6 | 87.7 | 81.7 | 2026-11-10 |
mlx-community/Qwen3.8-27B-4bit
Apple M5 Max |
128 GB | 3 | 82.1 | 95.6 | 76.9 | 77.5 | 90.4 | 83.9 | 2026-11-05 |
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 |
Tiel-Coder-35B-A3B-MLX-oQ4e-MTP
Apple M5 Max |
128 GB | 3 | 82.0 | 170.4 | 79.2 | 83.5 | 82.8 | 82.6 | 2026-10-17 |
cyber-tiel-coder-35b-a3b-mtp-ud
NVIDIA GeForce RTX 3060 |
12 GB | 8 | 82.0 | 35.3 | 74.2 | 83.7 | 84.7 | 85.6 | 2026-11-13 |
qwen3.8-flash-next-unsloth-ud-iq4_xs-v31
AMD Radeon RX 7900 XTX |
24 GB | 7 | 81.7 | 62.5 | 58.3 | 91.0 | 90.5 | 87.1 | 2026-11-11 |
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 |
qwen3.8-flash-next-iq3_s
Quadro RTX 5000 with Max-Q Design |
16 GB | 3 | 81.5 | 59.7 | 57.3 | 92.6 | 92.8 | 83.1 | 2026-11-02 |
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
NVIDIA GeForce RTX 4070 |
12 GB | 6 | 81.2 | 40.0 | 72.0 | 82.9 | 87.3 | 82.8 | 2026-11-01 |
qwen3.8-flash-next-unsloth-ud-iq4_xs
NVIDIA GeForce RTX 4090 |
24 GB | 10 | 80.9 | 57.4 | 58.6 | 90.4 | 92.5 | 82.2 | 2026-11-12 |
qwen/qwen3.6-35b-a3b
Apple M1 Max |
64 GB | 11 | 80.0 | 62.3 | 74.4 | 82.2 | 86.3 | 77.2 | 2026-11-04 |
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 |
Thinklite-27-GGUF_t1p95k20m0
Tesla V100-PCIE-32GB |
32 GB | 3 | 79.9 | 48.6 | 60.2 | 87.9 | 89.6 | 81.8 | 2026-11-10 |
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 |
qwen3.8-flash-next-iq3_s
NVIDIA GeForce RTX 3090 |
24 GB | 6 | 78.6 | 83.2 | 61.4 | 75.8 | 90.3 | 86.9 | 2026-11-14 |
Kwaipilot-KAT-Coder_t1p95k20m0
Tesla V100-PCIE-32GB |
32 GB | 8 | 78.3 | 100.6 | 71.4 | 72.4 | 86.9 | 82.6 | 2026-11-10 |
qwen3.8-flash-next-unsloth-ud-q4_k_xl
NVIDIA GeForce RTX 3060 |
12 GB | 3 | 78.1 | 32.7 | 54.0 | 87.7 | 92.7 | 78.0 | 2026-11-13 |
qwen/qwen3.8-27b
NVIDIA GeForce RTX 5060 Ti |
16 GB | 3 | 78.0 | 18.2 | 62.8 | 80.1 | 86.9 | 82.4 | 2026-11-11 |
unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
Apple M4 Max |
128 GB | 3 | 77.9 | 197.0 | 74.2 | 81.8 | 77.1 | 78.2 | 2026-11-11 |
minicpm-v-4.7-35b-a3b-q6_k
AMD Radeon RX 7800 XT |
16 GB | 3 | 77.9 | 25.1 | 63.4 | 86.9 | 88.5 | 72.9 | 2026-11-15 |
default
AMD Radeon RX 7900 XTX |
24 GB | 4 | 77.5 | 56.2 | 52.4 | 89.5 | 89.8 | 78.3 | 2026-11-03 |
swift-1.5-9b-q8_0
AMD Radeon RX 9050 / 9060 XT |
16 GB | 3 | 77.2 | 32.1 | 49.3 | 86.4 | 86.0 | 87.1 | 2026-11-05 |
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 |
Qwen3.8-Flash-Next-Avalon-IQ3KS-00001-of-00033
Advanced Micro Devices, Inc. [AMD/ATI] Device 7550 |
16 GB | 10 | 76.8 | 39.4 | 62.4 | 76.8 | 86.5 | 81.5 | 2026-11-14 |
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 |
gpt-oss:20b
AMD Radeon RX 7600 XT |
16 GB | 3 | 76.6 | 54.2 | 74.0 | 83.4 | 69.2 | 79.6 | 2026-11-07 |
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 |
qwen/qwen3.8-27b
AMD Radeon RX 7900 XTX |
24 GB | 3 | 76.5 | 39.7 | 48.7 | 85.3 | 87.6 | 84.4 | 2026-11-10 |
qwen3.6:35b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 4 | 76.2 | 31.1 | 66.7 | 72.7 | 86.3 | 79.2 | 2026-11-08 |
qwen/qwen3.8-27b
Apple M1 Max |
64 GB | 11 | 76.2 | 15.8 | 64.5 | 75.4 | 83.5 | 81.4 | 2026-11-04 |
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 |
Kwaipilot-KAT-Coder
Tesla V100-PCIE-32GB |
32 GB | 6 | 76.0 | 83.7 | 69.9 | 65.3 | 85.3 | 83.5 | 2026-11-09 |
gemma4:31b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 5 | 76.0 | 4.5 | 67.5 | 80.0 | 80.9 | 75.8 | 2026-11-12 |
Ornith-1.5-35B-A3B.APEX-I-NanoPlus
AMD Radeon RX 9070/9070 XT/9070 GRE |
16 GB | 3 | 75.8 | 126.6 | 81.2 | 61.7 | 74.3 | 86.1 | 2026-10-18 |
huihui-qwen3.6-35b-a3b-abliterated-q5_k
NVIDIA GeForce RTX 4070 |
12 GB | 3 | 75.4 | 134.4 | 77.5 | 64.9 | 85.2 | 74.1 | 2026-11-14 |
Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit
Apple M4 Pro |
48 GB | 10 | 75.4 | 114.3 | 70.5 | 73.9 | 82.4 | 74.9 | 2026-11-04 |
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 |
swift-1.5-9b-q6_k
AMD Radeon RX 9050 / 9060 XT |
16 GB | 6 | 75.3 | 39.7 | 59.7 | 72.6 | 83.8 | 85.0 | 2026-11-05 |
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 |
unsloth/gemma-4-31B-it-qat-GGUF
Apple M5 Max |
64 GB | 4 | 74.9 | 50.6 | 70.8 | 82.8 | 79.6 | 66.5 | 2026-11-14 |
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 |
gemma4:26b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 5 | 74.6 | 39.6 | 66.3 | 80.3 | 79.6 | 72.1 | 2026-11-12 |
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 |
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0
Apple M4 Max |
128 GB | 4 | 74.1 | 102.2 | 62.7 | 69.9 | 84.5 | 79.5 | 2026-11-11 |
gemma4:12b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 8 | 74.1 | 56.0 | 65.8 | 80.4 | 79.1 | 71.0 | 2026-11-12 |
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 |
gemma-4-26b-a4b
AMD Radeon AI PRO R9700 |
32 GB | 3 | 73.1 | 198.1 | 63.9 | 83.0 | 84.8 | 60.7 | 2026-11-14 |
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 |
coder
AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M |
16 GB | 4 | 72.5 | 42.3 | 55.0 | 68.2 | 85.8 | 81.0 | 2026-11-05 |
swift-1.5-9b
AMD Radeon RX 9050 / 9060 XT |
16 GB | 16 | 72.3 | 40.0 | 44.7 | 74.6 | 85.7 | 84.2 | 2026-11-12 |
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 |
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 |
Qwen3.6-35B-A3B-oQ4e-mtp
Apple M4 Pro |
48 GB | 19 | 71.4 | 100.1 | 65.9 | 65.1 | 78.9 | 75.8 | 2026-10-19 |
google/gemma-4-26b-a4b
Apple M1 Max |
64 GB | 5 | 71.3 | 101.0 | 65.7 | 79.3 | 78.0 | 62.2 | 2026-11-02 |
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 |
gemma-4-E4B-it-M-TS-Q4_K_M
NVIDIA GeForce RTX 3060 |
12 GB | 5 | 70.9 | 81.1 | 61.7 | 80.4 | 78.4 | 63.3 | 2026-11-02 |
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 |
nemotron-bolt:THINKING
AMD Radeon Graphics |
24 GB | 3 | 70.5 | 134.7 | 65.8 | 79.3 | 76.1 | 60.9 | 2026-11-01 |
gemma4:latest
AMD Radeon 8060S |
8 GB | 14 | 70.5 | 82.7 | 56.2 | 80.0 | 79.3 | 66.3 | 2026-11-15 |
gemma4:e4b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 4 | 69.8 | 99.4 | 60.6 | 73.1 | 78.3 | 67.4 | 2026-11-08 |
gemma4:e4b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 18 | 69.8 | 97.6 | 61.6 | 76.5 | 76.8 | 64.2 | 2026-11-12 |
gemma4:latest
Apple M2 Pro |
16 GB | 13 | 69.6 | 132.4 | 60.6 | 72.8 | 74.0 | 71.1 | 2026-11-14 |
qwen3.8-9b-distill
NVIDIA A10G |
24 GB | 3 | 69.3 | 115.6 | 58.2 | 60.7 | 84.3 | 73.8 | 2026-11-03 |
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:9b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 13 | 68.7 | 44.8 | 57.7 | 68.7 | 74.9 | 73.5 | 2026-11-12 |
ornith-1.5-9b
AMD Radeon RX 9050 / 9060 XT |
16 GB | 8 | 68.7 | 44.0 | 40.2 | 63.0 | 86.3 | 85.3 | 2026-11-05 |
gemma4:e2b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 36 | 68.2 | 153.3 | 57.1 | 71.2 | 75.8 | 68.7 | 2026-11-12 |
ornith-1.5:9b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 3 | 67.9 | 41.7 | 65.1 | 70.0 | 61.0 | 75.5 | 2026-11-12 |
nemotron-3.5-bolt:e4b
NVIDIA RTX 3500 Ada Generation Laptop GPU |
12 GB | 7 | 67.8 | 82.8 | 57.2 | 79.0 | 74.2 | 60.7 | 2026-11-12 |
nemotron-3.5-bolt:e4b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 3 | 67.5 | 79.9 | 61.3 | 73.2 | 68.9 | 66.5 | 2026-11-01 |
qwen_coder
NVIDIA GeForce GTX 1080 Ti |
11 GB | 3 | 67.3 | 39.0 | 63.9 | 68.9 | 75.6 | 60.8 | 2026-11-07 |
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/Qwen3-30B-A3B-Thinking-2507-GGUF
NVIDIA GeForce RTX 3080 |
10 GB | 9 | 66.7 | 44.7 | 48.0 | 73.6 | 77.3 | 67.9 | 2026-11-07 |
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 |
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0
Apple M5 Ultra |
96 GB | 3 | 66.4 | 150.8 | 43.8 | 61.0 | 80.2 | 80.5 | 2026-11-05 |
a3-qwen3.5-9b
NVIDIA A10G |
24 GB | 3 | 66.2 | 114.8 | 61.1 | 65.0 | 67.1 | 71.5 | 2026-11-04 |
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 |
google/gemma-4-12b
Apple M1 Max |
64 GB | 4 | 65.4 | 26.9 | 40.9 | 77.7 | 78.2 | 64.7 | 2026-11-04 |
qwen3.8-9b-distill-mlx@4bit
Apple M1 Max |
64 GB | 3 | 65.0 | 44.4 | 44.6 | 79.2 | 77.2 | 58.9 | 2026-11-03 |
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 |
ministral-3:8b
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 3 | 64.1 | 21.9 | 52.8 | 63.4 | 76.9 | 63.3 | 2026-11-01 |
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-e4b
Apple M5 Max |
64 GB | 7 | 62.9 | 53.8 | 44.8 | 69.8 | 74.6 | 62.2 | 2026-11-06 |
google/gemma-4-e2b
Apple M1 Max |
64 GB | 12 | 62.2 | 75.6 | 43.8 | 72.4 | 77.4 | 55.1 | 2026-11-04 |
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 |
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 |
Apex-35B-V1.0_t1p95k20m0
Tesla V100-PCIE-32GB |
32 GB | 3 | 57.0 | 99.1 | 28.9 | 30.3 | 84.5 | 84.4 | 2026-11-10 |
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 |
mistralai/ministral-3-3b
NVIDIA GeForce RTX 2050 |
4 GB | 4 | 54.0 | 26.4 | 33.8 | 52.4 | 71.2 | 58.5 | 2026-10-30 |
ministral-3-3b-instruct-2512
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 3 | 54.0 | 13.3 | 34.8 | 59.4 | 69.7 | 52.0 | 2026-10-31 |
mistralai/ministral-3-3b
NVIDIA GeForce GTX 1080 Ti |
11 GB | 3 | 53.6 | 72.6 | 39.4 | 52.6 | 75.1 | 47.3 | 2026-11-05 |
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 |
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 |
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 |
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 |
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 |
gemma-3-4b-it
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 3 | 46.8 | 12.6 | 23.7 | 30.5 | 80.6 | 52.4 | 2026-11-13 |
Ministral-3-3B-Instruct-2512-GGUF
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 46.2 | 20.1 | 35.2 | 40.0 | 56.5 | 53.2 | 2026-11-10 |
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 |
hf.co/ibm-granite/granite-4.0-h-tiny-GGUF:Q4_K_M
NVIDIA RTX 2000 Ada Generation Laptop GPU |
8 GB | 3 | 42.4 | 142.7 | 33.2 | 47.3 | 45.9 | 43.0 | 2026-11-01 |
schematron-3b
NVIDIA GeForce RTX 2050 |
4 GB | 3 | 39.6 | 37.8 | 8.3 | 59.7 | 56.6 | 33.8 | 2026-10-30 |
qwen2.5-coder:7b
NVIDIA GeForce RTX 3070 |
8 GB | 5 | 37.4 | 48.6 | 42.3 | 30.0 | 39.7 | 37.6 | 2026-11-03 |
LFM3-Omni-2B-Q8_0
NVIDIA GeForce RTX 3060 |
12 GB | 4 | 37.0 | 136.3 | 6.0 | 68.9 | 32.1 | 40.9 | 2026-11-02 |
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 |
qwen3.5-2b
NVIDIA GeForce GTX 1050 |
2 GB | 4 | 35.6 | 14.7 | 21.4 | 35.4 | 55.0 | 30.7 | 2026-11-11 |
unsloth/gemma-3-1b-it-GGUF
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 5 | 34.8 | 33.8 | 5.8 | 48.0 | 58.5 | 26.9 | 2026-11-13 |
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 |
ternary-bonsai-2-2b
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 6 | 34.1 | 38.2 | 13.0 | 34.3 | 57.9 | 31.3 | 2026-11-02 |
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 |
llama-3.2-3b-instruct
NVIDIA GeForce GTX 1050 |
2 GB | 3 | 29.9 | 6.6 | 6.9 | 23.0 | 58.4 | 31.2 | 2026-11-11 |
prism-ml/Ternary-Bonsai-1.7B-gguf
AMD Radeon Vega Series / Radeon Vega Mobile Series |
2 GB | 3 | 29.1 | 37.8 | 1.6 | 56.2 | 39.2 | 19.4 | 2026-11-13 |
Qwen-HighTemp
Tesla V100-PCIE-32GB |
32 GB | 9 | 25.6 | 234.5 | 9.3 | 42.2 | 28.2 | 22.6 | 2026-11-10 |
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 |
Qwen-LowTemp
Tesla V100-PCIE-32GB |
32 GB | 10 | 24.7 | 224.6 | 5.5 | 68.1 | 11.1 | 14.0 | 2026-11-10 |
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 |
qwen:latest
NVIDIA GeForce RTX 3060 |
12 GB | 10 | 9.5 | 75.0 | 3.0 | 19.2 | 10.6 | 5.0 | 2026-11-10 |
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 |
models 0
None public yet