Claude Code · Claude · GPT · AI Agent · huggingface.co
By default, Qwen3.8 retains thinking blocks from all historical messages
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
This repository contains FP8-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
Key facts
- Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, they are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date
- In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools
- Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks
- For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetition
Summary
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. For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools.