gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
76 vs 75
Hardware Fit
46 vs 50
Quality Score
89 vs 86
Hardware
gemma4:31b qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM64 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma4:31b qwen2.5:72b
Tokens/sec22.44.4
First chunk565 ms529 ms
TTFT30.0 s529 ms
Load time6.9 s49.7 s
Memory usage43.9 GB54.0 GB
Memory %69%44%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen2.5:72b
Speed
4/50
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
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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