gpt-oss-20b

THINKING MODEL

Mac mini (Apple M4 Pro)

64 GB · macOS 15.7.4

Tested on March 6, 2026

Top 0% Compare

Global Score

95 /100

Excellent

Hardware Fit

94/100

Quality

95/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 14 total (10 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 64 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.7.4
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 118.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±65.9
First chunk latency Delay before the first streamed chunk arrives from runtime: 471 ms
Time to first token How fast the model starts responding — lower is better: 2.2 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 11.3 GB (18%)
Total tokens Total number of tokens generated across all benchmark prompts: 1615
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~500

Score breakdown

Speed

50/50

Time to first token

14/20

Memory

30/30

Quality

Reasoning

19/20

Coding

18/20

Instruction following

18/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.6+1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 2bd7c556351ee18a250d6b27843d3631d447b9c069419f05a7c6a8a0abbfa12e

Interpretation

Hardware fit: 94/100. Overall suitability: EXCELLENT (Global 95/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Token speed is unstable (stddev 65.9 tok/s, mean 118.2 tok/s) — may indicate thermal throttling or memory pressure.

Bench Environment

Power: AC CPU load: avg 32% (peak 40%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest