Tencent Mixue releases a new model
The story so far
Tencent Mixuan has released the Qwen3.8-27B-DSpine-b16 pre-trained model, which includes 27B parameters, b16 precision, 5 layers of Draft layers, and an 8,192 token sliding window, designed to improve efficiency during inference and needs to be used in conjunction with the Qwen3.8-27B model. This model is used in the DSpine system. When using it, you need to set the --model-path and --speculative-draft-model-path parameters and use the tokenizer, token embedding, and LM head of the target model. The model began training on October 27, 2026, and the current checkpoint comes from data step 18,210 and optimizer step 18,000.
AI-written from the reports · Updated 11 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Tencent Hunyuan · Hugging Face new modelstencent/Qwen3.8-27B-DSpine-b16
Qwen3.8-27B-DSpine-b16 pre-trained model released by Mixue, featuring 27B parameters, b16 precision, 5 layers of Draft layers, and an 8,192 token sliding window, designed to improve efficiency during inference and must be used with the Qwen3.8-27B model.