gpt-oss-safeguard-20b-mlx

gpt_oss · 20B · MXFP4

THINKING MODEL

Mac mini (Apple M4)

24 GB · macOS 26.3

Tested on March 12, 2026 · Submitted by cryptoepops

Top 6% Compare

Global Score

87 /100

Excellent

Hardware Fit

82/100

Quality

89/100

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
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 41.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 8 ms
Time to first token How fast the model starts responding — lower is better: 3.6 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: 14.5 GB (61%)
Total tokens Total number of tokens generated across all benchmark prompts: 1880
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~367

Score breakdown

Speed

50/50

Time to first token

12/20

Memory

20/30

Quality

Reasoning

19/20

Coding

12/20

Instruction following

19/20

Structured output

15/15

Math

15/15

Multilingual

9/10

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 0.4.6+1
Model format: MLX
Hardware profile: ENTRY
Result hash: 7700e3e9fd5860939f641fe8c0341a16cb25d3ad116bc22303b063b39801710a

Interpretation

Hardware fit: 82/100. Overall suitability: EXCELLENT (Global 87/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Power: AC CPU load: avg 18% (peak 22%)

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