hf.co/ornith-ai/Ornith-1.0-9B-GGUF:Q8_0

OLLAMA GGUF

qwen35 · 8.95B · unknown

Marginal

Aug 23, 2026 · Apple M1 Pro

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score

57 vs 87

Hardware Fit

81 vs 82

Quality Score

46 vs 89

Hardware

hf.co/ornith-ai/Or… gpt-oss-safeguard-…

MachineMacBook ProMac mini

CPUApple M1 ProApple M4

Cores1010

RAM16 GB24 GB

GPUApple M1 ProApple M4

OSmacOS 26.6.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

hf.co/ornith-ai/Or… gpt-oss-safeguard-…

Tokens/sec18.641.4

First chunk303 ms8 ms

TTFT303 ms3.6 s

Load time4.6 sN/A

Memory usage10.1 GB14.5 GB

Memory %63%61%

HW Fit Score Breakdown

hf.co/ornith-ai/Ornith-…

Speed

42/50

TTFT

20/20

Memory

19/30

gpt-oss-safeguard-20b-mlx

Speed

50/50

TTFT

12/20

Memory

20/30

Quality

hf.co/ornith-ai/Ornith-…

Reasoning

14/20

Coding

13/20

Instruction

5/20

Structured

1/15

Math

13/15

Multilingual

0/10

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

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

View hf.co/ornith-ai/Or… details | View gpt-oss-safeguard-… 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