Instructions to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Lucebox/Laguna-XS-2.1-DFlash-GGUF",
	filename="laguna-xs21-dflash-q4.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Lucebox/Laguna-XS-2.1-DFlash-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/Laguna-XS-2.1-DFlash-GGUF
# Run inference directly in the terminal:
llama cli -hf Lucebox/Laguna-XS-2.1-DFlash-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Lucebox/Laguna-XS-2.1-DFlash-GGUF
# Run inference directly in the terminal:
llama cli -hf Lucebox/Laguna-XS-2.1-DFlash-GGUF

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/Laguna-XS-2.1-DFlash-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Lucebox/Laguna-XS-2.1-DFlash-GGUF

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/Laguna-XS-2.1-DFlash-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lucebox/Laguna-XS-2.1-DFlash-GGUF

Use Docker

docker model run hf.co/Lucebox/Laguna-XS-2.1-DFlash-GGUF

LM Studio
Jan
Ollama
How to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with Ollama:
```
ollama run hf.co/Lucebox/Laguna-XS-2.1-DFlash-GGUF
```

Unsloth Studio

How to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Lucebox/Laguna-XS-2.1-DFlash-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Lucebox/Laguna-XS-2.1-DFlash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Lucebox/Laguna-XS-2.1-DFlash-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/Lucebox/Laguna-XS-2.1-DFlash-GGUF
```

Lemonade

How to use Lucebox/Laguna-XS-2.1-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lucebox/Laguna-XS-2.1-DFlash-GGUF

Run and chat with the model

lemonade run user.Laguna-XS-2.1-DFlash-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Laguna-XS-2.1-DFlash-GGUF (quantized drafter)

Quantized GGUF builds of the official poolside/Laguna-XS-2.1-DFlash speculator, packaged for the Lucebox inference engine's speculative decoding of poolside/Laguna-XS-2.1.

file	scheme	size	notes
`laguna-xs21-dflash-q4.gguf`	Q4_0 projections, Q8_0 feature projection (fc), F32 norms	271 MB	recommended
`laguna-xs21-dflash-q8.gguf`	Q8_0 projections, F32 norms	492 MB	conservative

Because speculative decoding verifies every draft against the target model, drafter quantization cannot change the target's greedy output quality; the only quantity at stake is acceptance length. Measured on an RTX 3090 with the Laguna XS 2.1 Q4_K_M target (HumanEval/GSM8K/Math screens): acceptance unchanged vs the BF16 drafter, end-to-end decode ~+3% (q4), gold-scored task accuracy identical.

Produced with server/scripts/requant_dflash_draft.py from the lucebox engine tree (GGUF-to-GGUF requant; all metadata, gates and aux norms preserved).

License: OpenMDW-1.1, inherited from the base speculator. All credit for the DFlash speculator weights to poolside.