Leaderboard

Real benchmarks from real hardware. Compare local LLM performance across different setups. Run the command below to contribute yours.

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest

Trending

Last 7 days
Top Models
  • 1
    mistral:latest 1
  • 2
    llama3.2:latest 1
Top Machines
  • 1
    Micro-Star International Co., Ltd. MS-7B79 2
Top CPUs
  • 1
    AMD Ryzen 5 2600X Six-Core Processor 2

Benchmarks

283

total runs

Models

194

unique models

Families

44

model families

Hardware

22

unique CPUs

Get notified when new models & hardware are benchmarked
Filters

283 results

#CPUModelSizeRAMRuntimetok/sTTFTHW FitQualityGlobalFlagsVerdict
1Apple M2 Maxqwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx30B/MXFP496 GBLM-STUDIOMLX79.61.7 s
95
98
97
THINKExcellent
2Apple M4 Progpt-oss-20b—64 GBLM-STUDIOGGUF118.22.2 s
94
95
95
THINKExcellent
3Apple M2 Maxqwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx30B/MXFP496 GBLM-STUDIOMLX80.41.8 s
94
96
95
THINKExcellent
4Intel Core™ Ultra 9 285Kgpt-oss:20b20.9B/MXFP447 GBOLLAMAGGUF239.9616 ms
98
94
95
THINKExcellent
5Apple M4openai/gpt-oss-20b20B/MXFP424 GBLM-STUDIOMLX29.31.8 s
99
93
95
THINKExcellent
6Apple M4 Progpt-oss:20b20.9B/MXFP448 GBOLLAMAGGUF54.52.9 s
92
95
94
THINKExcellent
7Apple M4openai/gpt-oss-20b20B/MXFP432 GBLM-STUDIOMLX40.71.3 s
100
92
94
THINKExcellent
8Apple M4qwen/qwen3-30b-a3b-250730B/4bit32 GBLM-STUDIOMLX44.8405 ms
100
91
94
Excellent
9Apple M4 Pronemotron-3-nano—64 GBLM-STUDIOGGUF93.3257 ms
100
90
93
THINKExcellent
10AMD RYZEN AI MAX+ 395gpt-oss:20b20.9B/MXFP4125 GBOLLAMAGGUF47.11.8 s
85
96
93
ECOTHINKExcellent
11AMD Ryzen 5 5500qwen/qwen3-vl-30b30B/Q4_K_M31 GBLM-STUDIOGGUF24.8735 ms
95
90
92
Excellent
12Intel Core™ Ultra 9 285Kqwen3-coder:30b30.5B/Q4_K_M47 GBOLLAMAGGUF207.9513 ms
96
87
90
Excellent
13AMD Ryzen 5 5500openai/gpt-oss-20b20B/MXFP431 GBLM-STUDIOGGUF58.74.5 s
88
91
90
THINKExcellent
14Apple M4unsloth/gemma-4-26b-a4b-it26B/Q3_K_M24 GBLM-STUDIOGGUF24.9817 ms
85
92
90
Excellent
15Apple M1 Maxqwen3:14b14.8B/Q4_K_M32 GBOLLAMAGGUF24.0300 ms
97
87
90
Excellent
16AMD RYZEN AI MAX+ 395nemotron-3-nano:latest31.6B/Q4_K_M125 GBOLLAMAGGUF65.2295 ms
100
84
89
Excellent
17AMD RYZEN AI MAX+ 395gemma4:26b25.8B/Q4_K_M125 GBOLLAMAGGUF48.3346 ms
95
87
89
Excellent
18Apple M4 Proqwen/qwen3-8b8B/4bit64 GBLM-STUDIOMLX33.4257 ms
95
87
89
THINKExcellent
19AMD RYZEN AI MAX+ 395lfm2:24b23.8B/Q4_K_M125 GBOLLAMAGGUF95.4202 ms
100
83
88
Excellent
20AMD RYZEN AI MAX+ 395qwen3.6:35b-a3b36.0B/Q4_K_M125 GBOLLAMAGGUF43.3291 ms
91
87
88
ECOExcellent
...

Don't miss new benchmarks

Get notified when new models and hardware configurations are tested. No spam, unsubscribe anytime.