openai/gpt-oss-20b

gpt_oss · 20B · MXFP4

THINKING MODEL

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 4, 2026 · Submitted by Topaz750

Top 2% Compare

Global Score

94 /100

Excellent

Hardware Fit

100/100

Quality

92/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 40.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±3.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 824 ms
Time to first token How fast the model starts responding — lower is better: 1.3 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 (35%)
Total tokens Total number of tokens generated across all benchmark prompts: 1386
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~21

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

20/20

Coding

18/20

Instruction following

15/20

Structured output

14/15

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: 0.2.0
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: 18550517d598d307f9cb85e6f23fa79c5b56a9e81f7171dc7f4b3ce8251ba446

Interpretation

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

Bench Environment

Power: AC CPU load: avg 11% (peak 13%)

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