qwen2.5:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 1, 2026 · Apple M4
Gemma4-31B:31B
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
83 vs 76
Hardware Fit
80 vs 45
Quality Score
84 vs 89
Hardware
qwen2.5:14b Gemma4-31B:31B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen2.5:14b Gemma4-31B:31B
Tokens/sec11.23.8
First chunkN/A3536 ms
TTFT539 ms3.5 s
Load time1.0 s19.6 s
Memory usage16.5 GB19.9 GB
Memory %52%31%
HW Fit Score Breakdown
qwen2.5:14b
Speed
20/50
TTFT
30/20
Memory
30/30
Gemma4-31B:31B
Speed
5/50
TTFT
10/20
Memory
30/30
Quality
qwen2.5:14b
Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
Gemma4-31B:31B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
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