gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
76 vs 61
Hardware Fit
46 vs 85
Quality Score
89 vs 51
Hardware
gemma4:31b qwen3:0.6b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M4 MaxIntel Core™ i5-8350U
Cores168
RAM64 GB23 GB
GPUApple M4 MaxKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3.1Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:31b qwen3:0.6b
Tokens/sec22.427.0
First chunk565 ms597 ms
TTFT30.0 s8.7 s
Load time6.9 s1.8 s
Memory usage43.9 GB0.9 GB
Memory %69%4%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
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
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate 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