gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
76 vs 39
Hardware Fit
46 vs 100
Quality Score
89 vs 13
Hardware
gemma4:31b starcoder2:3b
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 starcoder2:3b
Tokens/sec22.449.4
First chunk565 msN/A
TTFT30.0 s155 ms
Load time6.9 s0.4 s
Memory usage43.9 GB3.0 GB
Memory %69%9%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
starcoder2:3b
Speed
40/50
TTFT
30/20
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
starcoder2:3b
Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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