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
    gemma4:31b 1
Top Machines
  • 1
    MacBook Pro 1
Top CPUs
  • 1
    Apple M4 Max 1

Benchmarks

244

total runs

Models

173

unique models

Families

42

model families

Hardware

17

unique CPUs

Get notified when new models & hardware are benchmarked
Filters

244 results

#CPUModelSizeRAMRuntimetok/sTTFTHW FitQualityGlobalFlagsVerdict
1Apple M4 Progpt-oss-20b—64 GBLM-STUDIOGGUF118.22.2 s
94
95
95
THINKExcellent
2Intel Core™ Ultra 9 285Kgpt-oss:20b20.9B/MXFP447 GBOLLAMAGGUF239.9616 ms
98
94
95
THINKExcellent
3Apple M4openai/gpt-oss-20b20B/MXFP424 GBLM-STUDIOMLX29.31.8 s
99
93
95
THINKExcellent
4Apple M4openai/gpt-oss-20b20B/MXFP432 GBLM-STUDIOMLX40.71.3 s
100
92
94
THINKExcellent
5Apple M4qwen/qwen3-30b-a3b-250730B/4bit32 GBLM-STUDIOMLX44.8405 ms
100
91
94
Excellent
6Apple M4 Pronemotron-3-nano—64 GBLM-STUDIOGGUF93.3257 ms
100
90
93
THINKExcellent
7AMD RYZEN AI MAX+ 395gpt-oss:20b20.9B/MXFP4125 GBOLLAMAGGUF47.11.8 s
85
96
93
ECOTHINKExcellent
8Intel Core™ Ultra 9 285Kqwen3-coder:30b30.5B/Q4_K_M47 GBOLLAMAGGUF207.9513 ms
96
87
90
Excellent
9Apple M4unsloth/gemma-4-26b-a4b-it26B/Q3_K_M24 GBLM-STUDIOGGUF24.9817 ms
85
92
90
Excellent
10Apple M1 Maxqwen3:14b14.8B/Q4_K_M32 GBOLLAMAGGUF24.0300 ms
97
87
90
Excellent
11AMD RYZEN AI MAX+ 395nemotron-3-nano:latest31.6B/Q4_K_M125 GBOLLAMAGGUF65.2295 ms
100
84
89
Excellent
12AMD RYZEN AI MAX+ 395gemma4:26b25.8B/Q4_K_M125 GBOLLAMAGGUF48.3346 ms
95
87
89
Excellent
13Apple M4 Proqwen/qwen3-8b8B/4bit64 GBLM-STUDIOMLX33.4257 ms
95
87
89
THINKExcellent
14AMD RYZEN AI MAX+ 395lfm2:24b23.8B/Q4_K_M125 GBOLLAMAGGUF95.4202 ms
100
83
88
Excellent
15AMD RYZEN AI MAX+ 395lfm2:24b23.8B/Q4_K_M125 GBOLLAMAGGUF85.3123 ms
100
83
88
Excellent
16Apple M4gpt-oss-orchestrator:latest20.9B/MXFP424 GBOLLAMAGGUF24.64.8 s
80
91
88
THINKExcellent
17AMD RYZEN AI MAX+ 395qwen3.5:35b-a3b36.0B/Q4_K_M125 GBOLLAMAGGUF42.0243 ms
90
87
88
Excellent
18Apple M4gpt-oss:20b20.9B/MXFP424 GBOLLAMAGGUF24.34.5 s
83
88
87
THINKExcellent
19Apple M4gpt-oss-safeguard-20b-mlx20B/MXFP424 GBLM-STUDIOMLX41.43.6 s
82
89
87
THINKExcellent
20AMD RYZEN AI MAX+ 395nemotron-3-nano:latest31.6B/Q4_K_M125 GBOLLAMAGGUF59.9199 ms
100
82
87
Excellent
...

Don't miss new benchmarks

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