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

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

lmstudio-community/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score

76 vs 77

Hardware Fit

77 vs 68

Quality Score

76 vs 81

Hardware

qwen3.6:35b-a3b-co… lmstudio-community…

MachineMacBook ProDocker Container

CPUApple M4 ProIntel Gen Intel® Core™ i9-11900H

Cores1416

RAM48 GB15 GB

GPUApple M4 ProTigerLake-H GT1 [UHD Graphics]

OSmacOS 26.4.1Ubuntu 26.04 LTS

Archarm64x64

Power Modebalancedperformance

Performance

qwen3.6:35b-a3b-co… lmstudio-community…

Tokens/sec72.711.4

First chunk147 ms28 ms

TTFT30.0 s2.2 s

Load time5.7 s6.8 s

Memory usage19.6 GB0.6 GB

Memory %41%4%

HW Fit Score Breakdown

qwen3.6:35b-a3b-coding-…

Speed

50/50

TTFT

0/20

Memory

27/30

lmstudio-community/gemm…

Speed

21/50

TTFT

17/20

Memory

30/30

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

lmstudio-community/gemm…

Reasoning

14/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

View qwen3.6:35b-a3b-co… details | View lmstudio-community… 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