gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
83 vs 50
Hardware Fit
65 vs 97
Quality Score
90 vs 30
Hardware
gpt-oss:20b gemma3:270m
MachineMac miniMacBook Pro
CPUApple M4Apple M3 Pro
Cores1012
RAM24 GB36 GB
GPUApple M4Apple M3 Pro
OSmacOS 26.3macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b gemma3:270m
Tokens/sec17.1239.2
First chunk705 ms127 ms
TTFT10.2 s127 ms
Load time23.1 s0.7 s
Memory usage13.1 GB0.6 GB
Memory %55%2%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
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