Model Intelligence Sheet
grapeV-ai/Qwen3.6-27B-DFlash-GGUF overview
What is this? Qwen3.6 27B https://huggingface.co/Qwen/Qwen3.6 27B の投機的デコード用モジュール Qwen3.6 27B DFlash https://huggingface.co/z lab/Qwen3.6 27B DFlash/tree/main を…
Runs locally from ~719.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
7 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.6-27B-DFlash-DFlash-BF16.gguf | GGUF | BF16 | 3.23 GB | Download |
| Qwen3.6-27B-DFlash-Q3_K_L.gguf | GGUF | Q3_K_L | 861.5 MB | Download |
| Qwen3.6-27B-DFlash-Q3_K_M.gguf | GGUF | Q3_K_M | 794.0 MB | Download |
| Qwen3.6-27B-DFlash-Q3_K_S.gguf | GGUF | Q3_K_S | 719.7 MB | Download |
| Qwen3.6-27B-DFlash-Q4_K_M.gguf | GGUF | Q4_K_M | 985.2 MB | Download |
| Qwen3.6-27B-DFlash-Q5_K_M.gguf | GGUF | Q5_K_M | 1.14 GB | Download |
| Qwen3.6-27B-DFlash-Q6_K.gguf | GGUF | Q6_K | 1.33 GB | Download |
Model Details
Model README
---
license: mit
---
What is this?
Qwen3.6-27Bの投機的デコード用モジュールQwen3.6-27B-DFlashをGGUFフォーマットに変換したものです。<br>
こちらのGGUFは単体ではご利用いただけません。Qwen3.6-27B本体のGGUFと併せて使用することで、トークン生成を高速化できます。
Note
-md このGGUFのパス --spec-type draft-dflash --spec-draft-n-max 3でDFlash投機的デコードが有効化されます。
License
MIT License
Developer
z-lab
Run grapeV-ai/Qwen3.6-27B-DFlash-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models