gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
50 vs 75
Hardware Fit
97 vs 50
Quality Score
30 vs 86
Hardware
gemma3:270m qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M3 ProCortex-X925
Cores1220
RAM36 GB122 GB
GPUApple M3 ProDevice 2e12
OSmacOS 15.7.5Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma3:270m qwen2.5:72b
Tokens/sec239.24.4
First chunk127 ms529 ms
TTFT127 ms529 ms
Load time0.7 s49.7 s
Memory usage0.6 GB54.0 GB
Memory %2%44%
HW Fit Score Breakdown
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
gemma3:270m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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