gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
76 vs 81
Hardware Fit
46 vs 96
Quality Score
89 vs 75
Hardware
gemma4:31b qwen3:8b
MachineMacBook ProASUS
CPUApple M4 MaxIntel Core™ i5-14600KF
Cores1620
RAM64 GB32 GB
GPUApple M4 MaxNVIDIA GeForce RTX 4070 Ti SUPER
OSmacOS 26.3.1Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:31b qwen3:8b
Tokens/sec22.4109.1
First chunk565 ms190 ms
TTFT30.0 s190 ms
Load time6.9 s4.3 s
Memory usage43.9 GB5.6 GB
Memory %69%18%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3:8b
Speed
50/50
TTFT
20/20
Memory
26/30
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
qwen3:8b
Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong 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