qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

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

90 vs 22

Hardware Fit

98 vs 50

Quality Score

86 vs 10

Hardware

qwen3.6-35b-a3b-cl… deepseek-r1:14b

MachineMacBook ProMacBook Air

CPUApple M5 MaxApple M4

Cores1810

RAM64 GB32 GB

GPUApple M5 MaxApple M4

OSmacOS 27.0macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b-cl… deepseek-r1:14b

Tokens/sec86.611.4

First chunk13 msN/A

TTFT143 ms30.0 s

Load timeN/A1.0 s

Memory usage23.9 GB16.5 GB

Memory %37%52%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

Speed

50/50

TTFT

20/20

Memory

28/30

deepseek-r1:14b

Speed

20/50

TTFT

0/20

Memory

30/30

Quality

qwen3.6-35b-a3b-claude-…

Reasoning

18/20

Coding

17/20

Instruction

14/20

Structured

15/15

Math

12/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong 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-a3b-cl… 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