gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
94 vs 84
Hardware Fit
92 vs 69
Quality Score
95 vs 91
Hardware
gpt-oss:20b gptoss · 20.9B · M…
MachineMacBook ProMac Pro
CPUApple M4 ProIntel Core™ i5-10400
Cores1412
RAM48 GB32 GB
GPUApple M4 ProAMD Radeon RX 6700 XT
OSmacOS 26.4.1macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b gptoss · 20.9B · M…
Tokens/sec54.517.5
First chunk318 ms643 ms
TTFT2.9 s7.7 s
Load time4.0 s0.0 s
Memory usage16.4 GB0.8 GB
Memory %34%3%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
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
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