What are the hardware requirements for Qwen3.5 397B A17B MXFP8 AutoRound?

Qwen3.5 397B A17B MXFP8 AutoRound requires approximately 189.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 397B A17B MXFP8 AutoRound and how large is it?

Qwen3.5 397B A17B MXFP8 AutoRound is developed by intel-ai, a model with 397b 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 Qwen3.5 397B A17B MXFP8 AutoRound?

Qwen3.5 397B A17B MXFP8 AutoRound is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 397B A17B MXFP8 AutoRound by intel-ai — VRAM 189.2GB

Name: Qwen3.5 397B A17B MXFP8 AutoRound
Author: intel-ai

Qwen3.5 397B A17B MXFP8 AutoRound is an open-source language model by intel-ai. Features: 397b LLM, VRAM: 189.2GB, License: apache-2.0, LLM Explorer Score: 0.3.

Arxiv:2309.05516 Auto-round Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a... Compressed-tensors Conversational Endpoints compatible Image-text-to-text Mxfp8 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/intel-ai/Qwen3.5-397B-A17B-MXFP8-AutoRound

Qwen3.5 397B A17B MXFP8 AutoRound Parameters and Internals

LLM Name	Qwen3.5 397B A17B MXFP8 AutoRound
Repository 🤗	https://huggingface.co/intel-ai/Qwen3.5-397B-A17B-MXFP8-AutoRound
Base Model(s)	Qwen/Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B
Model Size	397b
Required VRAM	189.2 GB
Updated	2026-11-10
Maintainer	intel-ai
Model Type	qwen3_5_moe
Model Files	4.4 GB: 1-of-94 4.4 GB: 2-of-94 4.4 GB: 3-of-94 4.4 GB: 4-of-94 4.4 GB: 5-of-94 4.4 GB: 6-of-94 4.4 GB: 7-of-94 4.4 GB: 8-of-94 4.4 GB: 9-of-94 4.4 GB: 10-of-94 4.4 GB: 11-of-94 4.4 GB: 12-of-94 4.4 GB: 13-of-94 4.4 GB: 14-of-94 4.4 GB: 15-of-94 4.4 GB: 16-of-94 4.4 GB: 17-of-94 4.4 GB: 18-of-94 4.4 GB: 19-of-94 4.4 GB: 20-of-94 4.4 GB: 21-of-94 4.4 GB: 22-of-94 4.4 GB: 23-of-94 4.4 GB: 24-of-94 4.4 GB: 25-of-94 4.4 GB: 26-of-94 4.4 GB: 27-of-94 4.4 GB: 28-of-94 4.4 GB: 29-of-94 4.4 GB: 30-of-94 4.4 GB: 31-of-94 4.4 GB: 32-of-94 4.4 GB: 33-of-94 4.4 GB: 34-of-94 4.4 GB: 35-of-94 4.4 GB: 36-of-94 4.4 GB: 37-of-94 4.4 GB: 38-of-94 4.4 GB: 39-of-94 4.4 GB: 40-of-94 4.4 GB: 41-of-94 4.4 GB: 42-of-94 4.4 GB: 43-of-94
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 397B A17B MXFP8 AutoRound 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 Qwen3.5 397B A17B MXFP8 AutoRound

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 397B A17B	0K / 369.8 GB	331990	1549
Qwen3.5 397B A17B NVFP4	0K / 251.1 GB	428565	102
Qwen3.5 397B A17B NVFP4 V2	0K / 243.5 GB	23781	5
Ornith 1.0 397B FP8	0K / 147.7 GB	597119	183
Ornith 1.0 397B	0K / 288.5 GB	186340	262
Qwen3.5 397B A17B	0K / 369.8 GB	53	13
Qwen3.5 397B A17B FP8	0K / 184.9 GB	825515	182
XYZ Aquila Pro	0K / 225 GB	1805	375
Qwen3.5 MoE	0K / 0 GB	268176	4
Ornith 1.5 397B	0K / 279.9 GB	672	66

Note: green Score (e.g. "73.2") means that the model is better than intel-ai/Qwen3.5-397B-A17B-MXFP8-AutoRound.