What are the hardware requirements for Qwen3.6 35B A3B FP8 Dynamic?

Qwen3.6 35B A3B FP8 Dynamic requires approximately 38.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B FP8 Dynamic and how large is it?

Qwen3.6 35B A3B FP8 Dynamic 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.

Where can I download or evaluate Qwen3.6 35B A3B FP8 Dynamic?

Qwen3.6 35B A3B FP8 Dynamic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 35B A3B FP8 Dynamic by axteam — VRAM 38.7GB

Name: Qwen3.6 35B A3B FP8 Dynamic
Author: axteam

Qwen3.6 35B A3B FP8 Dynamic is an open-source language model by axteam. Features: 35b LLM, VRAM: 38.7GB, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Compressed-tensors Conversational Endpoints compatible Fp8 Image-text-to-text 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-FP8-dynamic

Qwen3.6 35B A3B FP8 Dynamic Parameters and Internals

LLM Name	Qwen3.6 35B A3B FP8 Dynamic
Repository 🤗	https://huggingface.co/axteam/Qwen3.6-35B-A3B-FP8-dynamic
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	38.7 GB
Updated	2026-10-31
Maintainer	axteam
Model Type	qwen3_5_moe
Model Files	2.6 GB: 1-of-26 1.0 GB: 2-of-26 1.7 GB: 3-of-26 1.7 GB: 4-of-26 1.7 GB: 5-of-26 2.0 GB: 6-of-26 0.6 GB: 7-of-26 2.0 GB: 8-of-26 0.6 GB: 9-of-26 2.0 GB: 10-of-26 0.6 GB: 11-of-26 1.7 GB: 12-of-26 0.8 GB: 13-of-26 1.7 GB: 14-of-26 0.8 GB: 15-of-26 2.0 GB: 16-of-26 0.6 GB: 17-of-26 2.0 GB: 18-of-26 0.6 GB: 19-of-26 1.7 GB: 20-of-26 0.8 GB: 21-of-26 1.7 GB: 22-of-26 1.7 GB: 23-of-26 1.7 GB: 24-of-26 2.5 GB: 25-of-26 1.9 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 FP8 Dynamic 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 FP8 Dynamic

Best Alternatives	Context / RAM	Downloads	Likes
....5 35B A3B Sceptic V3 1M W4A16	1024K / 26.1 GB	223	0
...AgentWorld 35B A3B Abliterated	256K / 69.2 GB	962	18
Ornith 1.5 35B A3B NPU2	256K / GB	58	0
Qwen3.6 35B A3B NPU2	256K / GB	82	0
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
JEV 35B	0K / 72.3 GB	713162	403
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1426253	519
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343

Note: green Score (e.g. "73.2") means that the model is better than axteam/Qwen3.6-35B-A3B-FP8-dynamic.