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

Qwen3.6 35B A3B requires approximately 72.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Qwen3.6 35B A3B is developed by Qwen, 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 perform on standard benchmarks?

Qwen3.6 35B A3B 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 by Qwen — VRAM 72.2GB

Name: Qwen3.6 35B A3B
Rating: 3.5 (2 reviews)
Author: Qwen

Qwen3.6 35B A3B is an open-source language model by Qwen. Features: 35b LLM, VRAM: 72.2GB, License: apache-2.0, LLM Explorer Score: 0.64, ELO: 1395.

Conversational Deploy:azure Deploy:sagemaker Endpoints compatible Eval-results Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3.6-35B-A3B

Qwen3.6 35B A3B 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 Parameters and Internals

LLM Name	Qwen3.6 35B A3B
Repository 🤗	https://huggingface.co/Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	72.2 GB
Updated	2026-08-08
Maintainer	Qwen
Model Type	qwen3_5_moe
Model Files	4.0 GB: 1-of-26 1.3 GB: 2-of-26 3.4 GB: 3-of-26 3.4 GB: 4-of-26 3.4 GB: 5-of-26 4.0 GB: 6-of-26 1.1 GB: 7-of-26 4.0 GB: 8-of-26 1.1 GB: 9-of-26 4.0 GB: 10-of-26 1.1 GB: 11-of-26 3.4 GB: 12-of-26 1.6 GB: 13-of-26 3.4 GB: 14-of-26 1.6 GB: 15-of-26 4.0 GB: 16-of-26 1.1 GB: 17-of-26 4.0 GB: 18-of-26 1.1 GB: 19-of-26 3.4 GB: 20-of-26 1.6 GB: 21-of-26 3.4 GB: 22-of-26 3.4 GB: 23-of-26 3.4 GB: 24-of-26 3.8 GB: 25-of-26 2.2 GB: 26-of-26
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B 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

Quantized Models of the Qwen3.6 35B A3B

Model	Likes	Downloads	VRAM
...till 35B A3B Coder Abliterated	15	43572	12 GB
Qwen3.6 35B A3B AWQ	32	1020709	25 GB
Qwen3.6 35B A3B MLX 4bit	6	513193	20 GB
Qwen3.6 35B A3B GPTQ Int4	29	282964	22 GB
Qwen3.6 35B A3B MLX 6bit	2	478592	28 GB
Qwen3.6 35B A3B MLX 8bit	1	473537	37 GB
Qwen3.6 35B A3B UD MLX 4bit	112	15720	21 GB
Qwen3.6 35B A3B OQ4e Fp16 Mtp	1	187	22 GB
Qwen3.6 35B A3B MLX 8bit	41	3862	37 GB
Qwen3.6 35B A3B 2Bit GSQ	7	2119	13 GB

Best Alternatives to Qwen3.6 35B A3B

Best Alternatives	Context / RAM	Downloads	Likes
...AgentWorld 35B A3B Abliterated	256K / 69.2 GB	962	18
Ornith 1.5 35B A3B NPU2	256K / GB	136	1
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1909944	506
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
Qwen3.8 35B A3B Distill	0K / 69.9 GB	3532	49
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen3.6 35B A3B NVFP4 Fast	0K / 23.6 GB	463661	98