qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 2, 2026 · Apple M4
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest