gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
76 vs 64
Hardware Fit
46 vs 100
Quality Score
89 vs 48
Hardware
gemma4:31b microsoft/phi-4-mi…
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4 Pro
Cores1614
RAM64 GB64 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.3.1macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:31b microsoft/phi-4-mi…
Tokens/sec22.490.3
First chunk565 ms198 ms
TTFT30.0 s198 ms
Load time6.9 sN/A
Memory usage43.9 GB2.0 GB
Memory %69%3%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
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
microsoft/phi-4-mini-re…
Reasoning
7/20
Coding
7/20
Instruction
7/20
Structured
7/15
Math
13/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
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