gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
94 vs 87
Hardware Fit
92 vs 79
Quality Score
95 vs 90
Hardware
gpt-oss:20b gpt-oss:20b
MachineMacBook ProMac mini
CPUApple M4 ProApple M4
Cores1410
RAM48 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 26.4.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b gpt-oss:20b
Tokens/sec54.526.4
First chunk318 ms505 ms
TTFT2.9 s6.7 s
Load time4.0 s10.5 s
Memory usage16.4 GB13.1 GB
Memory %34%55%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
23/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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