openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Apr 1, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
Global Score
82 vs 87
Hardware Fit
85 vs 83
Quality Score
81 vs 88
Hardware
openai/gpt-oss-20b gpt-oss:20b
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b gpt-oss:20b
Tokens/sec31.824.3
First chunk32 ms529 ms
TTFT8.4 s4.5 s
Load time22.7 s11.2 s
Memory usage0.0 GB13.1 GB
Memory %0%55%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
5/20
Memory
30/30
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
Quality
openai/gpt-oss-20b
Reasoning
19/20
Coding
14/20
Instruction
9/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
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