gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

granite3.1-dense:8b

OLLAMA GGUF

granite · 8.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

87 vs 74

Hardware Fit

82 vs 91

Quality Score

89 vs 66

Hardware

gpt-oss-safeguard-… granite3.1-dense:8b

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-… granite3.1-dense:8b

Tokens/sec41.418.8

First chunk8 msN/A

TTFT3.6 s308 ms

Load timeN/A0.6 s

Memory usage14.5 GB13.0 GB

Memory %61%41%

HW Fit Score Breakdown

gpt-oss-safeguard-20b-mlx

Speed

50/50

TTFT

12/20

Memory

20/30

granite3.1-dense:8b

Speed

31/50

TTFT

30/20

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

granite3.1-dense:8b

Reasoning

12/20

Coding

11/20

Instruction

15/20

Structured

14/15

Math

5/15

Multilingual

9/10

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

View gpt-oss-safeguard-… details | View granite3.1-dense:8b 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