gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
83 vs 84
Hardware Fit
65 vs 69
Quality Score
90 vs 91
Hardware
gpt-oss:20b gptoss · 20.9B · M…
MachineMac miniMac Pro
CPUApple M4Intel Core™ i5-10400
Cores1012
RAM24 GB32 GB
GPUApple M4AMD Radeon RX 6700 XT
OSmacOS 26.3macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b gptoss · 20.9B · M…
Tokens/sec17.117.5
First chunk705 ms643 ms
TTFT10.2 s7.7 s
Load time23.1 s0.0 s
Memory usage13.1 GB0.8 GB
Memory %55%3%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
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