Back to leaderboard

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
87 vs 65
Hardware Fit
82 vs 96
Quality Score
89 vs 51

Hardware

gpt-oss-safeguard-… qwen3-4b-qwen3.6-p…
MachineMac miniMac Studio
CPUApple M4Apple M2 Max
Cores1012
RAM24 GB96 GB
GPUApple M4Apple M2 Max
OSmacOS 26.3macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gpt-oss-safeguard-… qwen3-4b-qwen3.6-p…
Tokens/sec41.499.6
First chunk8 ms18 ms
TTFT3.6 s1.6 s
Load timeN/A4.8 s
Memory usage14.5 GB0.3 GB
Memory %61%0%

HW Fit Score Breakdown

gpt-oss-safeguard-20b-mlx

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

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
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

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

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