openai/gpt-oss-20b

gpt_oss · 20B · MXFP4

THINKING MODEL

MacBook Pro (Apple M5 Max)

128 GB · macOS 26.6.2

Tested on September 29, 2026 · Submitted by mOOnSPa

Top 30% Compare

Global Score

83 /100

Not Rec.

Hardware Fit

80/100

Quality

84/100

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 M5 Max
Cores: 18 threads (6 cores)
Frequency: 2.4 GHz
RAM: 128 GB LPDDR5
GPU: Apple M5 Max
OS: macOS 26.6.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 138.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±2.3
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: 30.0 s
Load time Time to load the model into memory before inference: 6.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.5 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1708
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~956

Score breakdown

Speed

50/50

Time to first token

0/20

Memory

30/30

Quality

Reasoning

18/20

Coding

12/20

Instruction following

15/20

Structured output

14/15

Math

15/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.3.33+1
Model format: MLX
Hardware profile: HIGH-END
Result hash: 967f9cd1f61ebca8012bf5478b99bd304b3f6f870f9c154a1b79669c09d5c6d6

Interpretation

Hardware fit: 80/100. Overall suitability: NOT RECOMMENDED (Global 83/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Running on battery power — performance may be reduced.

Disqualifiers

Time to first token too high: 30000ms (maximum: 12250ms for HIGH-END profile)

Bench Environment

Power: Battery CPU load: avg 7% (peak 7%)

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