Qwen 发布 Qwen3.8-27B-FP8 视觉语言模型权重
Qwen 的 Hugging Face 仓库提供了后训练模型 Qwen3.8-27B-FP8 的 FP8 量化权重和配置文件，这是一款 27B 参数的视觉语言模型。相关产物采用 Hugging Face Transformers 格式，并据称兼容 Transformers、vLLM、SGLang 和 TokenSpeed。Qwen 表示，采用块大小为 128 的细粒度 FP8 量化后，模型性能与原模型几乎相同。
此次发布提供了采用 Apache 2.0 许可的 FP8 部署产物，便于开发者在主流推理框架中集成本地视觉语言模型。不过，“性能几乎相同”的说法由厂商自述，报告未提供独立基准验证。
Qwen/Qwen3.8-27B-FP8 Image-Text-to-Text • 28B • Updated 3 days ago • 5.29M • 980
base_model:
- Qwen/Qwen3.8-27B library_name: transformers license: apache-2.0 pipeline_tag: image-text-to-text
Qwen3.8-27B-FP8
[!Note] This repository contains FP8-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc. The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original model.
#Qwen#Qwen3.8-27B-FP8#Hugging Face Transformers#vLLM#SGLang#TokenSpeed#Qwen Cloud