Best local LLM for French

Mistral AI's Small 3.1 — Small 3 plus a vision encoder, a 128k context, and ~150 tok/s inference under Apache 2.0. Small 3.2 (June 2025) is a drop-in upgrade.

Mistral AI's June 2025 refresh of Small 3.1: a 24B Apache 2.0 dense model with vision input, sharper function calling, and roughly half the rate of runaway generations seen in 3.1.

Mistral AI's first open reasoning model, built on Small 3.1 with RL-trained chain-of-thought. Hits 70.7% on AIME24 under Apache 2.0.

Mistral AI and NVIDIA's co-developed 12B instruct model with 128k context, the Tekken tokenizer, and strong European multilingual coverage.

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

Mistral AI's 24B dense model that closes most of the gap with 70B-class models. Best quality-per-parameter we've measured at this size in 2025.

Mistral AI's open frontier TTS model covering 9 languages including French, rivaling ElevenLabs on quality. Note: CC-BY-NC 4.0, non-commercial only.

Utter Project's 22.6B EU-sovereign model released February 2026 covering 35 European languages with 32k context — the heavy-duty successor to EuroLLM 9B.