qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score

80 vs 47

Hardware Fit

77 vs 53

Quality Score

81 vs 45

Hardware

qwen3.6:35b-mlx qwen3:4b

MachineMacBook ProMacBook Air

CPUApple M5 MaxApple M4

Cores1810

RAM48 GB32 GB

GPUApple M5 MaxApple M4

OSmacOS 26.5.2macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

qwen3.6:35b-mlx qwen3:4b

Tokens/sec129.811.3

First chunk77 msN/A

TTFT30.0 s9.2 s

Load time1.8 s0.1 s

Memory usage19.7 GB7.2 GB

Memory %41%23%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed

50/50

TTFT

0/20

Memory

27/30

qwen3:4b

Speed

17/50

TTFT

6/20

Memory

30/30

Quality

qwen3.6:35b-mlx

Reasoning

19/20

Coding

9/20

Instruction

18/20

Structured

11/15

Math

14/15

Multilingual

10/10

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

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

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

View qwen3.6:35b-mlx details | View qwen3:4b 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