# Qwen3.5-397B-A17B MoE GPTQ Int4 quantized variant published on Hugging Face

> Qwen published a GPTQ 4-bit quantized version of the Qwen3.5-397B-A17B MoE model on Hugging Face. Pipeline tag is image-text-to-text, library is transformers, licensed Apache 2.0.

| | |
|---|---|
| **Tool** | Qwen |
| **Version** | — |
| **Kind** | release |
| **Published** | 2026-03-03 |
| **Observed** | 2026-08-11 |
| **Significance** | 1/5 |
| **Breaking** | no |
| **Categories** | — |

> **Note:** this classification is below our confidence threshold and is pending human review.

## What changed


- Model: `Qwen/Qwen3.5-397B-A17B-GPTQ-Int4`
- Pipeline: image-text-to-text
- Library: transformers
- License: Apache 2.0
- Tags: qwen3_5_moe, 4-bit, gptq, endpoints_compatible, region:us, deploy:azure
- Repository created: 2026-03-03


## Sources

- [hf_model](https://huggingface.co/Qwen/Qwen3.5-397B-A17B-GPTQ-Int4) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/qwen/qwen3-5-397b-a17b-moe-gptq-int4-quantized-variant-published-on-hugging-face
Entity: https://changelogs.info/qwen
Event ID: `evt_2026-03-03_qwen_qwen-qwen3-5-397b-a17b-gptq-int4`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.