qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

deepseek-r1:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score

80 vs 22

Hardware Fit

77 vs 50

Quality Score

81 vs 10

Hardware

qwen3.6:35b-mlx deepseek-r1:14b

MachineMacBook ProMacBook Air

CPUApple M5 MaxApple M4

Cores1810

RAM48 GB32 GB

GPUApple M5 MaxApple M4

OSmacOS 26.5.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.6:35b-mlx deepseek-r1:14b

Tokens/sec129.811.4

First chunk77 msN/A

TTFT30.0 s30.0 s

Load time1.8 s1.0 s

Memory usage19.7 GB16.5 GB

Memory %41%52%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed

50/50

TTFT

0/20

Memory

27/30

deepseek-r1:14b

Speed

20/50

TTFT

0/20

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

deepseek-r1:14b

Reasoning

1/20

Coding

3/20

Instruction

1/20

Structured

0/15

Math

0/15

Multilingual

5/10

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

View qwen3.6:35b-mlx details | View deepseek-r1:14b 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