Tencent Hunyuan · Hugging Face new models·· 7 days ago22
tencent/Qwen3.8-27B-DSpine-b16
tencent/Qwen3.8-27B-DSpine-b16
Brief overview
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.
Article
DSpine draft weights for Qwen3.8-27B.
| Property | Value |
|---|---|
| Draft layers | 5 |
| Block size | 16 |
| Sliding window | 8,192 tokens |
| Precision | BF16 |
Training started on October 27, 2026. This checkpoint is from data step 18,210 and optimizer step 18,000.
Usage
Follow the Qwen3.8-27B inference instructions
in DSpine. Set --model-path to Qwen/Qwen3.8-27B and
--speculative-draft-model-path to this model repository or its local directory.
The tokenizer, token embeddings and LM head are supplied by the target model.
Source: Tencent Hunyuan · Hugging Face new models · huggingface.co