qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score

73 vs 87

Hardware Fit

100 vs 82

Quality Score

61 vs 89

Hardware

qwen2.5-coder-3b-i… gpt-oss-safeguard-…

MachineMacBook AirMac mini

CPUApple M4Apple M4

Cores1010

RAM32 GB24 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5-coder-3b-i… gpt-oss-safeguard-…

Tokens/sec52.341.4

First chunk285 ms8 ms

TTFT285 ms3.6 s

Load timeN/AN/A

Memory usage1.6 GB14.5 GB

Memory %5%61%

HW Fit Score Breakdown

qwen2.5-coder-3b-instru…

Speed

50/50

TTFT

20/20

Memory

30/30

gpt-oss-safeguard-20b-mlx

Speed

50/50

TTFT

12/20

Memory

20/30

Quality

qwen2.5-coder-3b-instru…

Reasoning

7/20

Coding

14/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

9/10

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

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 qwen2.5-coder-3b-i… 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