Back to leaderboard

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
79 vs 78
Hardware Fit
95 vs 47
Quality Score
72 vs 92

Hardware

qwen2.5-coder:7b gemma4:31b
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen2.5-coder:7b gemma4:31b
Tokens/sec22.19.8
First chunkN/A873 ms
TTFT285 ms873 ms
Load time0.8 s7.0 s
Memory usage7.6 GB68.3 GB
Memory %24%55%

HW Fit Score Breakdown

qwen2.5-coder:7b

Speed
35/50
TTFT
30/20
Memory
30/30

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

Quality

qwen2.5-coder:7b

Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest