Lucebox/Qwen3.8-27B-DFlash2-GGUF overview
Qwen3.8 27B DFlash2 drafter GGUF The DFlash2 draft model used by the qualified Qwen 3.8 27B profile on Lucebox https://www.lucebox.com appliances. Lucebox Mana…
Runs locally from ~1.90 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.8-27B-DFlash2-Q8_0.gguf | GGUF | Q8_0 | 1.90 GB | Download |
Model Details
Model README
---
library_name: gguf
base_model: Qwen/Qwen3.8-27B
tags:
- gguf
- speculative-decoding
- dflash
---
Qwen3.8-27B DFlash2 drafter (GGUF)
The DFlash2 draft model used by the qualified Qwen 3.8 27B profile on
Lucebox appliances. Lucebox Manage downloads this file
and verifies it byte for byte before installing the profile.
| | |
|---|---|
| file | Qwen3.8-27B-DFlash2-Q8_0.gguf |
| size | 2,045,471,776 bytes |
| sha256 | bb727abc583498aa4deea8b3cd0c34c2d96553954cbff25b5f7bdd469f0f1306 |
Pair it with the target model
at Qwen3.8-27B-UD-IQ4_XS.gguf.
The DFlash2 block-diffusion drafter design comes from
z-lab/dflash. This is a separate build from the
public z-lab/Qwen3.8-27B-DFlash2-GGUF
weights and the two files are not interchangeable for the byte-exact check above.
Run Lucebox/Qwen3.8-27B-DFlash2-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models