openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 19, 2026 · Apple M4
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
77 vs 50
Hardware Fit
67 vs 97
Quality Score
81 vs 30
Hardware
openai/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
openai/gpt-oss-20b gemma3:270m
Tokens/sec30.5239.2
First chunk18 ms127 ms
TTFT30.0 s127 ms
Load timeN/A0.7 s
Memory usage15.8 GB0.6 GB
Memory %66%2%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
17/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
openai/gpt-oss-20b
Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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