GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

canhdu/Qwen3.6-27B-DFlash-GGUF overview

This repository stores Z Lab's Qwen3.6 27B DFlash drafter quantized to Q4 K M and Q8 0 using upstream llama.cpp and following spiritbuun's guide https://huggin…

ggufdflashspeculative-decodingdiffusionefficiencyflash-decodingqwendiffusion-language-modelbase_model:z-lab/Qwen3.6-27B-DFlashbase_model:quantized:z-lab/Qwen3.6-27B-DFlashlicense:mitendpoints_compatibleregion:usconversational

Runs locally from ~985.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
dflash-draft-3.6-q4_k_m.ggufGGUFQ4_K_M985.2 MBDownload
dflash-draft-3.6-q8_0.ggufGGUFQ8_01.72 GBDownload

Model Details

Model IDcanhdu/Qwen3.6-27B-DFlash-GGUF
Authorcanhdu
Pipeline
Licensemit
Base modelz-lab/Qwen3.6-27B-DFlash
Last modified2026-07-30T03:14:18.000Z

Model README

---

license: mit

base_model:

  • z-lab/Qwen3.6-27B-DFlash

tags:

- dflash

- speculative-decoding

- diffusion

- efficiency

- flash-decoding

- qwen

- diffusion-language-model

---

This repository stores Z Lab's Qwen3.6 27B DFlash drafter quantized to Q4_K_M and Q8_0 using upstream llama.cpp and following spiritbuun's guide.

Run canhdu/Qwen3.6-27B-DFlash-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models