gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
88 vs 50
Hardware Fit
86 vs 97
Quality Score
89 vs 30
Hardware
gemma4:12b-it-qat gemma3:270m
MachineMac miniMacBook Pro
CPUApple M4 ProApple M3 Pro
Cores1212
RAM24 GB36 GB
GPUApple M4 ProApple M3 Pro
OSmacOS 15.6.1macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat gemma3:270m
Tokens/sec30.0239.2
First chunk686 ms127 ms
TTFT7.1 s127 ms
Load time5.4 s0.7 s
Memory usage7.1 GB0.6 GB
Memory %30%2%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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