openai/gpt-oss-20b

gpt-oss · 20B · MXFP4

THINKING MODEL

MacBook Pro (Apple M3 Max)

128 GB · macOS 27.2

Tested on November 9, 2026

Top 5% Compare

Global Score

91 /100

Excellent

Hardware Fit

90/100

Quality

91/100

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 Pro
CPU: Apple M3 Max
Cores: 16 total (12 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 128 GB LPDDR5
GPU: Apple M3 Max
OS: macOS 27.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 95.1
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 3 ms
Time to first token How fast the model starts responding — lower is better: 2.5 s
Load time Time to load the model into memory before inference: 9.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1713
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~906

Score breakdown

Speed

50/50

Time to first token

10/20

Memory

30/30

Quality

Reasoning

18/20

Coding

15/20

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 0.4.12+1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: c945afe210c11d3175ed009c64bb2c8417ac74fc2d040d8409b834a645de0853

Interpretation

Hardware fit: 90/100. Overall suitability: EXCELLENT (Global 91/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 42% (peak 54%)

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