What are the hardware requirements for Qwen3.5 397B A17B MXFP4?

Qwen3.5 397B A17B MXFP4 requires approximately 98.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 397B A17B MXFP4 and how large is it?

Qwen3.5 397B A17B MXFP4 is developed by amd, 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 MXFP4?

Qwen3.5 397B A17B MXFP4 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 MXFP4 by amd — VRAM 98.9GB

Name: Qwen3.5 397B A17B MXFP4
Author: amd

Qwen3.5 397B A17B MXFP4 is an open-source language model by amd. Features: 397b LLM, VRAM: 98.9GB, License: apache-2.0, LLM Explorer Score: 0.29.

8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a... Conversational En Endpoints compatible Image-text-to-text Quark Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4

Qwen3.5 397B A17B MXFP4 Parameters and Internals

LLM Name	Qwen3.5 397B A17B MXFP4
Repository 🤗	https://huggingface.co/amd/Qwen3.5-397B-A17B-MXFP4
Base Model(s)	Qwen/Qwen3.5-397B-A17B-FP8 Qwen/Qwen3.5-397B-A17B-FP8
Model Size	397b
Required VRAM	98.9 GB
Updated	2026-08-09
Maintainer	amd
Model Type	qwen3_5_moe
Model Files	2.3 GB: 1-of-94 2.3 GB: 2-of-94 2.3 GB: 3-of-94 2.3 GB: 4-of-94 2.3 GB: 5-of-94 2.3 GB: 6-of-94 2.3 GB: 7-of-94 2.3 GB: 8-of-94 2.3 GB: 9-of-94 2.3 GB: 10-of-94 2.3 GB: 11-of-94 2.3 GB: 12-of-94 2.3 GB: 13-of-94 2.3 GB: 14-of-94 2.3 GB: 15-of-94 2.3 GB: 16-of-94 2.3 GB: 17-of-94 2.3 GB: 18-of-94 2.3 GB: 19-of-94 2.3 GB: 20-of-94 2.3 GB: 21-of-94 2.3 GB: 22-of-94 2.3 GB: 23-of-94 2.3 GB: 24-of-94 2.3 GB: 25-of-94 2.3 GB: 26-of-94 2.3 GB: 27-of-94 2.3 GB: 28-of-94 2.3 GB: 29-of-94 2.3 GB: 30-of-94 2.3 GB: 31-of-94 2.3 GB: 32-of-94 2.3 GB: 33-of-94 2.3 GB: 34-of-94 2.3 GB: 35-of-94 2.3 GB: 36-of-94 2.3 GB: 37-of-94 2.3 GB: 38-of-94 2.3 GB: 39-of-94 2.3 GB: 40-of-94 2.3 GB: 41-of-94 2.3 GB: 42-of-94 2.3 GB: 43-of-94
Supported Languages	en
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 397B A17B MXFP4 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 MXFP4

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	0K / 288.5 GB	318396	260
Ornith 1.0 397B FP8	0K / 147.7 GB	597119	183
XYZ Aquila Pro	0K / 225 GB	1805	375
Qwen3.5 397B A17B	0K / 369.8 GB	53	13
Qwen3.5 397B A17B FP8	0K / 184.9 GB	825515	182
Ornith 1.0 397B	0K / 288.5 GB	447	4
...7B A17B Heretic Int4 AutoRound	0K / 212.3 GB	4351	4

Note: green Score (e.g. "73.2") means that the model is better than amd/Qwen3.5-397B-A17B-MXFP4.