qwen3.6:35b-a3b-coding-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

huihui-devstral-small-2-24b-instruct-2512-abliterated-i1

LM-STUDIO GGUF

mistral3 · 24B · Q4_K_S

Good

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score

76 vs 78

Hardware Fit

77 vs 74

Quality Score

76 vs 79

Hardware

qwen3.6:35b-a3b-co… huihui-devstral-sm…

MachineMacBook ProSystem manufacturer

CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor

Cores1416

RAM48 GB32 GB

GPUApple M4 ProAMD Radeon RX 9060 XT

OSmacOS 26.4.1Microsoft Windows 11 Home 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

qwen3.6:35b-a3b-co… huihui-devstral-sm…

Tokens/sec72.717.5

First chunk147 ms20 ms

TTFT30.0 s279 ms

Load time5.7 sN/A

Memory usage19.6 GB15.6 GB

Memory %41%49%

HW Fit Score Breakdown

qwen3.6:35b-a3b-coding-…

Speed

50/50

TTFT

0/20

Memory

27/30

huihui-devstral-small-2…

Speed

29/50

TTFT

20/20

Memory

25/30

Quality

qwen3.6:35b-a3b-coding-…

Reasoning

19/20

Coding

9/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

10/10

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

huihui-devstral-small-2…

Reasoning

16/20

Coding

17/20

Instruction

15/20

Structured

14/15

Math

7/15

Multilingual

10/10

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

View qwen3.6:35b-a3b-co… details | View huihui-devstral-sm… 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