Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
77 vs 81
Hardware Fit
67 vs 59
Quality Score
81 vs 91

Hardware

qwen3.5-9b-mlx gpt-oss:20b
MachineMac miniGMKtec NucBox EVO-T2S
CPUApple M4 ProIntel Core™ Ultra X7 358H
Cores1416
RAM64 GB64 GB
GPUApple M4 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx gpt-oss:20b
Tokens/sec20.319.1
First chunk4216 ms1985 ms
TTFT4.2 s11.1 s
Load timeN/A7.7 s
Memory usage5.6 GB12.9 GB
Memory %9%20%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

gpt-oss:20b

Speed
26/50
TTFT
3/20
Memory
30/30

Quality

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gpt-oss:20b

Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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