Instructions to use Lucebox/Qwen3.8-27B-DFlash2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Lucebox/Qwen3.8-27B-DFlash2-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
Use Docker
docker model run hf.co/Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
- LM Studio
- Jan
- Ollama
How to use Lucebox/Qwen3.8-27B-DFlash2-GGUF with Ollama:
ollama run hf.co/Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use Lucebox/Qwen3.8-27B-DFlash2-GGUF with Docker Model Runner:
docker model run hf.co/Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
- Lemonade
How to use Lucebox/Qwen3.8-27B-DFlash2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lucebox/Qwen3.8-27B-DFlash2-GGUF:Q8_0
Run and chat with the model
lemonade run user.Qwen3.8-27B-DFlash2-GGUF-Q8_0
List all available models
lemonade list
- Atomic Chat
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
unsloth/Qwen3.8-27B-GGUF
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.
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for Lucebox/Qwen3.8-27B-DFlash2-GGUF
Base model
Qwen/Qwen3.8-27B