XNews

Alibaba releases Qwen3-Next-80B FP8 models with Transformers and vLLM compatibility

Alibaba announced Qwen3-Next-80B-A3B-Instruct-FP8 and Qwen3-Next-80B-A3B-Thinking-FP8, now fully compatible with Transformers, vLLM, and SGLang, and supporting FP8 precision for faster inference. The post links to Hugging Face and ModelScope for access.

Source posts