Back to leaderboard

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

qwen3.5-27b-claude-4.6-opus-distilled-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Not Rec.

Mar 10, 2026 · Apple M4

Global Score
87 vs 34
Hardware Fit
82 vs 21
Quality Score
89 vs 39

Hardware

gpt-oss-safeguard-… qwen3.5-27b-claude…
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gpt-oss-safeguard-… qwen3.5-27b-claude…
Tokens/sec41.46.1
First chunk8 ms7 ms
TTFT3.6 s22.9 s
Load timeN/AN/A
Memory usage14.5 GB19.8 GB
Memory %61%82%

HW Fit Score Breakdown

gpt-oss-safeguard-20b-mlx

Speed
50/50
TTFT
12/20
Memory
20/30

qwen3.5-27b-claude-4.6-…

Speed
12/50
TTFT
0/20
Memory
9/30

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

qwen3.5-27b-claude-4.6-…

Reasoning
1/20
Coding
14/20
Instruction
5/20
Structured
8/15
Math
4/15
Multilingual
7/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Adequate

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