qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

57 vs 71

Hardware Fit

61 vs 88

Quality Score

55 vs 63

Hardware

qwen3.5:9b qwen3.5-4b-mlx

MachineAZW GTR ProMacBook Air

CPUAMD RYZEN AI MAX+ 395Apple M4

Cores3210

RAM125 GB32 GB

GPUAMD Radeon 8060SApple M4

OSUbuntu 24.04.4 LTSmacOS 26.3

Archx64arm64

Power Modelow-powerbalanced

Performance

qwen3.5:9b qwen3.5-4b-mlx

Tokens/sec30.323.1

First chunk205 ms3279 ms

TTFT8.7 s3.3 s

Load time5.6 sN/A

Memory usage18.8 GB2.9 GB

Memory %15%9%

HW Fit Score Breakdown

qwen3.5:9b

Speed

30/50

TTFT

1/20

Memory

30/30

qwen3.5-4b-mlx

Speed

45/50

TTFT

13/20

Memory

30/30

Quality

qwen3.5:9b

Reasoning

17/20

Coding

2/20

Instruction

7/20

Structured

8/15

Math

12/15

Multilingual

9/10

Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3.5-4b-mlx

Reasoning

15/20

Coding

16/20

Instruction

6/20

Structured

6/15

Math

11/15

Multilingual

9/10

Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

View qwen3.5:9b details | View qwen3.5-4b-mlx 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