BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Lucie 7B

By OpenLLM-France · France

Updated 2026-07-13

chat fr
Parameters
7B
License
Apache 2.0
Context
4k
VRAM (Q4)
5 GB
Released
January 2025

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

VRAM REQUIRED (GB)812Q4_K_M5 GBQ5_K_M6 GBQ8_09 GBFP1616 GB
QuantizationVRAM required
Q4_K_M (recommended)5 GB
Q5_K_M6 GB
Q8_09 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.

In practice, Lucie 7B fits an 8 GB consumer card at Q4_K_M (5 GB). Stepping up to Q8_0 nearly doubles the footprint to 9 GB, and unquantized FP16 weights take 16 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, Lucie 7B needs roughly 8 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 12 tokens/sec on entry-level GPUs, on the order of 35 tokens/sec on a mid-range card, and up to 90 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches Lucie 7B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for Lucie 7B
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBQ5_K_M (6 GB used)
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopQ8_0 (9 GB used)
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTFP16 (16 GB used)
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopFP16 (16 GB used)
32 GBRTX 5090FP16 (16 GB used)

Which GPU should you buy to run Lucie 7B?

To run Lucie 7B locally at Q4, you need ~5 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).

Check RTX 5060 price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Published benchmark scores

BenchmarkScore
MMLU (fr)54.2
FrenchBench68

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

Typical workloads

In our catalog grid, Lucie 7B is filed under Formal French, Local Content — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: French-language output where quality matters.

Note the 4k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.

Architecture & training

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

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

Verdict

Pick it for sovereignty and provenance, not raw capability — the 4k context is the dealbreaker for most workloads.

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.

Similar models worth comparing

Frequently asked questions

How much VRAM does Lucie 7B need?

At the recommended Q4_K_M quantization, Lucie 7B needs about 5 GB of VRAM. Q8_0 takes 9 GB, and unquantized FP16 weights take 16 GB.

Can Lucie 7B run without a GPU?

Yes — with roughly 8 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does Lucie 7B support?

Lucie 7B supports a 4k-token context window (4,096 tokens).

Can I use Lucie 7B commercially?

Yes. Lucie 7B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.

How fast is Lucie 7B on consumer hardware?

Our compatibility engine estimates on the order of 35 tokens/sec on a mid-range GPU and up to 90 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of Lucie 7B should I download first?

Start with Q4_K_M (5 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at Q5_K_M.

Tools

Is Lucie 7B the right pick for you?

Compute self-hosted ROI → Back to catalog