# Qwen3.8-27B FP8 quantized model published

> Qwen published an FP8 quantized version of Qwen3.8-27B on Hugging Face under the Qwen organisation. The model is image-text-to-text (multimodal), conversational, Apache 2.0 licensed, and derived from the full-precision Qwen3.8-27B base. No capability or benchmark claims are made in the repository listing.

| | |
|---|---|
| **Tool** | Qwen |
| **Version** | — |
| **Kind** | release |
| **Published** | 2026-08-13 |
| **Observed** | 2026-08-21 |
| **Significance** | 1/5 |
| **Breaking** | no |
| **Categories** | feature |

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

## What changed


- FP8 quantized variant of Qwen3.8-27B (Qwen3.5 generation)
- Pipeline: image-text-to-text (multimodal)
- Library: transformers, safetensors format
- License: Apache 2.0
- Base model: Qwen/Qwen3.8-27B
- Tags: endpoints_compatible, region:us
- No capability, benchmark, or performance data in the source


## Sources

- [hf_model](https://huggingface.co/Qwen/Qwen3.8-27B-FP8) — retrieved 2026-08-21


## Community

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

---
Canonical: https://changelogs.info/qwen/qwen3-8-27b-fp8-quantized-model-published
Entity: https://changelogs.info/qwen
Event ID: `evt_2026-08-13_qwen_qwen-qwen3-8-27b-fp8`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.