Luciole-8B-Instruct-1.1-GGUF

Luciole-8B-Instruct-1.1-GGUF

Quantized GGUF copy of Luciole-8B-Instruct-1.1, an 8B text generation model for French and English, for running on your own computer. From LINAGORA's work in the OpenLLM-France consortium.

Made by OpenLLM-France on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds a GGUF quantized copy of Luciole-8B-Instruct-1.1, a text generation model of about 8.1B parameters that handles French and English. A 4-bit copy comes to roughly 4 GB by Hugging Face's estimate. The card is short and sends you to the original model's page for details on how the model works.

Who it suits: It suits developers and researchers who want an open French and English model they can run on their own machine.

Industry | Who uses it | How they use it | Example
Software | Developers of French-language apps | Run a local chat model behind their own tool | Draft replies in French for an internal assistant
Research | NLP researchers | Test how an open 8B model handles French | Compare its answers with another model's on the same prompts
Local AI | Hobbyists | Chat with a model that stays on their computer | Ask for a short summary of a pasted paragraph

Anyone who needs documented benchmarks or a ready hosted service can skip it.

Where to use it: You run it in a local app that reads GGUF files.

• Ollama, which the card points to for testing
• llama.cpp, which the card names for quantization details
• Windows, macOS or Linux, with Python, for downloading the files

Use case | Who | What they get back
Chat in French or English | Anyone | Replies generated on their own machine
Prototype a language feature | Developers | A local model to test prompts against
Compare open models | Researchers | Answers to run beside other 8B models

How to set it up: Setup is a download and a local app that can open GGUF files.

• Python, for the Hugging Face hub tools
• Disk space for the file you keep, roughly 4 GB at 4-bit
• A local app such as Ollama or a llama.cpp build

1. Install the Hugging Face hub tools.
2. Download the repository files.
3. Open one file in your local app. The card points to the Ollama test steps on the original model's page.

pip install -U huggingface_hub
hf download OpenLLM-France/Luciole-8B-Instruct-1.1-GGUF

How to use it: The card shows no run command of its own. You load the file in your local app and chat with it, in French or English. For the Ollama route, open the section on testing with Ollama on the original Luciole-8B-Instruct-1.1 page.

Example: You load the file and type, "Summarize this paragraph in two sentences." followed by your text. The model writes a short summary on your machine. You can ask the same thing in French and get a French reply.

For newcomers and experts: GGUF is a file format for running a model on your own computer, and quantizing shrinks it to fit. A good first try is to download the files, load them in Ollama or a llama.cpp app, and ask a short question in French.

For someone who knows the field, this is a quantized build of an 8.1B model, and the card names no quant types, benchmarks or training data. Check the original model's page for those before you rely on it.

Original Luciole-8B-Instruct-1.1
Quantized into GGUF
Loaded in a local runtime
You chat in French or English

Good to know: The card says LINAGORA developed it within the OpenLLM-France consortium, a France2030 project funded by Bpifrance.

• License: Apache-2.0
• Cost to run: none named
• Data it reaches: it downloads files from Hugging Face. The card names no account, web or clipboard access.

On Hugging Face, 13 November 2026

• Task: text generation
• Parameters: 8.1B
• Weights: about 4 GB at 4-bit (estimate)
• Formats: GGUF
• Downloads in the last 30 days: 281
• Likes: 7
• License: apache-2.0
• Languages: fr, en
• Based on: OpenLLM-France/Luciole-8B-Instruct-1.1
• Tags: gguf, openllm-france, text-generation, conversational

Links

• Model: https://huggingface.co/OpenLLM-France/Luciole-8B-Instruct-1.1-GGUF
• Files: https://huggingface.co/OpenLLM-France/Luciole-8B-Instruct-1.1-GGUF/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download OpenLLM-France/Luciole-8B-Instruct-1.1-GGUF

Then follow the usage in its model card. Nothing in this kit runs by itself.