---
base_model: z-lab/Qwen3.6-27B-DFlash
tags:
- transformers
- safetensors
- qwen3
- feature-extraction
- dflash
- speculative-decoding
- diffusion
- efficiency
- flash-decoding
- qwen
- diffusion-language-model
- text-generation
- custom_code
- arxiv:2602.06036
- license:mit
- text-generation-inference
- endpoints_compatible
- region:us
---

**Qwen 3.6 27B DFlash GGUF**

llama.cpp quantizations of [**z-lab DFlash draft model**](https://huggingface.co/z-lab/Qwen3.6-27B-DFlash) for [**Qwen 3.6 27B**](https://huggingface.co/Qwen/Qwen3.6-27B).