Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score
62 vs 87
Hardware Fit
35 vs 82
Quality Score
73 vs 89

Hardware

qwen3.5-4b-mlx gpt-oss-safeguard-…
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1410
RAM64 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx gpt-oss-safeguard-…
Tokens/sec0.041.4
First chunk5548 ms8 ms
TTFT5.5 s3.6 s
Load timeN/AN/A
Memory usage2.9 GB14.5 GB
Memory %5%61%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

gpt-oss-safeguard-20b-mlx

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

Quality

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong 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 qwen3.5-4b-mlx 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