gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 94
Hardware Fit
65 vs 91
Quality Score
90 vs 95
Hardware
gpt-oss:20b gpt-oss:20b
MachineMac miniFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB64 GB
GPUApple M4AMD Radeon(TM) 8060S Graphics
OSmacOS 26.3Microsoft Windows 11 Pro for Workstations 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b gpt-oss:20b
Tokens/sec17.148.0
First chunk705 ms357 ms
TTFT10.2 s2.3 s
Load time23.1 s0.2 s
Memory usage13.1 GB16.4 GB
Memory %55%26%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
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
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
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