Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Good

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
58 vs 79
Hardware Fit
68 vs 59
Quality Score
54 vs 88

Hardware

qwen3.5-9b-mlx GPT-20B:20b
MachineMac miniGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM24 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx GPT-20B:20b
Tokens/sec16.719.3
First chunk23 ms2004 ms
TTFT14.1 s10.4 s
Load timeN/A10.4 s
Memory usage7.8 GB12.9 GB
Memory %33%20%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

GPT-20B:20b

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

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate

GPT-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
11/20
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