Lucie 7B

Overview

A French-sovereign 7B model from OpenLLM-France, backed by CNRS and LINAGORA, with a fully transparent and auditable training corpus.

When to pick this model

• EU public-sector projects with data sovereignty requirements
• French-language content generation and editorial work
• Research needing reproducible, openly documented training data
• Regulated environments demanding training-data provenance
• Demonstrating non-US-trained alternatives to stakeholders

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	5 GB
Q5_K_M	6 GB
Q8_0	9 GB
FP16 (no quantization)	16 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

Benchmark	Score
MMLU (fr)	54.2
FrenchBench	68

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

• Full European data sovereignty story
• Publicly available training corpus
• Strong formal French output
• Backed by CNRS and LINAGORA

Limitations

• 4k context is too short for modern RAG or long docs
• Weaker English than Mistral or Llama at the same size
• Smaller ecosystem of fine-tunes and tools

Architecture & training

Architecture: Llama-like · 32 layers · trained on Jean Zay (CNRS)

Training: OpenLLM-France project · 100% transparent corpus, high proportion of FR.

Quick start

ollama run lucie:7b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.