gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
Global Score
76 vs 34
Hardware Fit
46 vs 58
Quality Score
89 vs 23
Hardware
gemma4:31b qwen3.5:latest
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4
Cores1610
RAM64 GB16 GB
GPUApple M4 MaxApple M4
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:31b qwen3.5:latest
Tokens/sec22.413.3
First chunk565 ms438 ms
TTFT30.0 s19.8 s
Load time6.9 s0.2 s
Memory usage43.9 GB8.0 GB
Memory %69%50%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
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
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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