What are the hardware requirements for Qwen3.6 35B A3B AWQ 4bit?

Qwen3.6 35B A3B AWQ 4bit requires approximately 22.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B AWQ 4bit and how large is it?

Qwen3.6 35B A3B AWQ 4bit is developed by axteam, 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 AWQ 4bit perform on standard benchmarks?

Qwen3.6 35B A3B AWQ 4bit 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 AWQ 4bit by axteam — VRAM 22.4GB

Name: Qwen3.6 35B A3B AWQ 4bit
Author: axteam

Qwen3.6 35B A3B AWQ 4bit is an open-source language model by axteam. Features: 35b LLM, VRAM: 22.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.42, ELO: 1395.

4bit Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Compressed-tensors Conversational Endpoints compatible Image-text-to-text Int4 Multimodal Quantized Qwen Qwen3 5 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/axteam/Qwen3.6-35B-A3B-AWQ-4bit

Qwen3.6 35B A3B AWQ 4bit 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 AWQ 4bit Parameters and Internals

LLM Name	Qwen3.6 35B A3B AWQ 4bit
Repository 🤗	https://huggingface.co/axteam/Qwen3.6-35B-A3B-AWQ-4bit
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	22.4 GB
Updated	2026-10-31
Maintainer	axteam
Model Type	qwen3_5_moe
Model Files	20.0 GB: 1-of-2 2.4 GB: 2-of-2 1.7 GB
AWQ Quantization	Yes
Quantization Type	awq\|4bit
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 AWQ 4bit 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 AWQ 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B AWQ	0K / 25.5 GB	1020709	32
Qwen3.6 35B A3B AWQ 8bit	0K / 38.7 GB	25	2
Qwen3.6 35B A3B AWQ 4bit	0K / 25 GB	1010785	93
Ornith 1.5 35B A3B AWQ INT4	0K / 24.4 GB	2008	1
Ornith 1.5 35B A3B AWQ INT4	0K / 26.2 GB	833	3
...AT Coder V2.5 Dev OrnithVision	0K / 24.5 GB	280	0
...tic Quality Inspector V1.0 AWQ	0K / 26.1 GB	81	1
JEV 35B AWQ INT4 W4A8	0K / 0.9 GB	27	1
Ornith 1.5 35B A3B AWQ FP8	0K / 39.8 GB	51	1
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6

Note: green Score (e.g. "73.2") means that the model is better than axteam/Qwen3.6-35B-A3B-AWQ-4bit.