What are the hardware requirements for Qwen3.6 35B A3B 5bit?

Qwen3.6 35B A3B 5bit requires approximately 24.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B 5bit and how large is it?

Qwen3.6 35B A3B 5bit is developed by mlx-community, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3.6 35B A3B 5bit perform on standard benchmarks?

Qwen3.6 35B A3B 5bit has the following published scores: LMSYS ELO 1395. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3.6 35B A3B 5bit by mlx-community — VRAM 24.7GB

Name: Qwen3.6 35B A3B 5bit
Author: mlx-community

Qwen3.6 35B A3B 5bit is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 24.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1395.

5-bit 5bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Conversational Image-text-to-text Mlx Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-5bit

Qwen3.6 35B A3B 5bit Benchmarks

LMSys ELO 1395 vs 1272 (so35) 9.7%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen3.6 35B A3B 5bit Parameters and Internals

LLM Name	Qwen3.6 35B A3B 5bit
Repository 🤗	https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-5bit
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	24.7 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen3_5_moe
Model Files	5.3 GB: 1-of-5 5.2 GB: 2-of-5 5.2 GB: 3-of-5 5.2 GB: 4-of-5 3.8 GB: 5-of-5
Quantization Type	5bit
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B 5bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3.6 35B A3B 5bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B 6bit	0K / 28.9 GB	2742	8
Qwen3.6 35B A3B 4bit	0K / 20.5 GB	62036	92
Qwen3.6 35B A3B 8bit	0K / 37.8 GB	120175	27
Ornith 1.0 35B 4bit	0K / 20.5 GB	6835	13
Qwen3.6 35B A3B OptiQ 4bit	0K / 22.1 GB	14730	44
Ornith 1.0 35B 8bit	0K / 37.8 GB	4463	8
Ornith 1.0 35B OptiQ 4bit	0K / 22.2 GB	1648	3
...der V2.5 Dev Vision OptiQ 4bit	0K / 22.9 GB	93	2

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.6-35B-A3B-5bit.