gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
76 vs 47
Hardware Fit
46 vs 67
Quality Score
89 vs 38
Hardware
gemma4:31b qwen3:8b
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM64 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:31b qwen3:8b
Tokens/sec22.418.7
First chunk565 msN/A
TTFT30.0 s12.1 s
Load time6.9 s1.2 s
Memory usage43.9 GB9.5 GB
Memory %69%30%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
Quality
gemma4:31b
Reasoning
16/20
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
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest