What are the hardware requirements for Qwen3.5 397B A17B GPTQ Int4?

Qwen3.5 397B A17B GPTQ Int4 requires approximately 92.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 397B A17B GPTQ Int4 and how large is it?

Qwen3.5 397B A17B GPTQ Int4 is developed by Qwen, 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 GPTQ Int4?

Qwen3.5 397B A17B GPTQ Int4 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 GPTQ Int4 by Qwen — VRAM 92.4GB

Name: Qwen3.5 397B A17B GPTQ Int4
Author: Qwen

Qwen3.5 397B A17B GPTQ Int4 is an open-source language model by Qwen. Features: 397b LLM, VRAM: 92.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a... Conversational Deploy:azure Endpoints compatible Gptq Image-text-to-text Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3.5-397B-A17B-GPTQ-Int4

Qwen3.5 397B A17B GPTQ Int4 Parameters and Internals

LLM Name	Qwen3.5 397B A17B GPTQ Int4
Repository 🤗	https://huggingface.co/Qwen/Qwen3.5-397B-A17B-GPTQ-Int4
Base Model(s)	Qwen/Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B
Model Size	397b
Required VRAM	92.4 GB
Updated	2026-08-08
Maintainer	Qwen
Model Type	qwen3_5_moe
Model Files	2.2 GB: 1-of-94 2.2 GB: 2-of-94 2.2 GB: 3-of-94 2.2 GB: 4-of-94 2.2 GB: 5-of-94 2.2 GB: 6-of-94 2.2 GB: 7-of-94 2.2 GB: 8-of-94 2.2 GB: 9-of-94 2.2 GB: 10-of-94 2.2 GB: 11-of-94 2.2 GB: 12-of-94 2.2 GB: 13-of-94 2.2 GB: 14-of-94 2.2 GB: 15-of-94 2.2 GB: 16-of-94 2.2 GB: 17-of-94 2.2 GB: 18-of-94 2.2 GB: 19-of-94 2.2 GB: 20-of-94 2.2 GB: 21-of-94 2.2 GB: 22-of-94 2.2 GB: 23-of-94 2.2 GB: 24-of-94 2.2 GB: 25-of-94 2.2 GB: 26-of-94 2.2 GB: 27-of-94 2.2 GB: 28-of-94 2.2 GB: 29-of-94 2.2 GB: 30-of-94 2.2 GB: 31-of-94 2.2 GB: 32-of-94 2.2 GB: 33-of-94 2.2 GB: 34-of-94 2.2 GB: 35-of-94 2.2 GB: 36-of-94 2.2 GB: 37-of-94 2.2 GB: 38-of-94 2.2 GB: 39-of-94 2.2 GB: 40-of-94 2.2 GB: 41-of-94 2.2 GB: 42-of-94
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 397B A17B GPTQ Int4 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 GPTQ Int4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 397B A17B 4bit	0K / 222.2 GB	7004	11
Qwen3.5 397B A17B 8bit	0K / 209.7 GB	105802	5
Ornith 1.0 397B Mlx 8bit	0K / 208.8 GB	855	3
Qwen3.5 397B A17B 6bit	0K / 238.5 GB	2598	2
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 GGUF	0K / 0.9 GB	63434	253
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	228483	262

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3.5-397B-A17B-GPTQ-Int4.