gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

87 vs 69

Hardware Fit

82 vs 50

Quality Score

89 vs 77

Hardware

gpt-oss-safeguard-… mistralai/devstral…

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gpt-oss-safeguard-… mistralai/devstral…

Tokens/sec41.45.7

First chunk8 ms5007 ms

TTFT3.6 s5.0 s

Load timeN/AN/A

Memory usage14.5 GB13.2 GB

Memory %61%41%

HW Fit Score Breakdown

gpt-oss-safeguard-20b-mlx

Speed

50/50

TTFT

12/20

Memory

20/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

gpt-oss-safeguard-20b-mlx

Reasoning

19/20

Coding

12/20

Instruction

19/20

Structured

15/15

Math

15/15

Multilingual

9/10

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

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View gpt-oss-safeguard-… details | View mistralai/devstral… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest