Mistral Large 4 hits Hugging Face, post-trainable with TRL on one 8xB300 node
SergioPaniego · x · 2026-10-29
Mistral Large 4 (codename "Le Chonk") is now live on the Hugging Face Hub — a 1T-parameter MoE with 52B active per token, shipping with a full chat template. The author also shared a companion blog showing how to post-train it with TRL: a ready-made SFT + LoRA example runs on a single 8xB300 node, so the community can fine-tune it right away.
More from Models
- Codex doubles usage limits for all Pro tiers after user backlash — pvncher · 2026-10-30
- Dream raises $17M seed from a16z to build spatial-reasoning AI for AEC — a16z · 2026-10-30
- Investor bets speech-to-speech will be massive, praises Phonic's model — graceisford · 2026-10-30
- User Praises OpenAI for Doubling Pro Usage and Including API in Pro Sub — Angaisb_ · 2026-10-30
- OpenAI doubles usage limits for Pro tiers and Business Premium, effective immediately — Polymarket · 2026-10-30
- Gemini 4 Argon tops 4 robotics tasks on RLE-Bench, ranks #2 behind GPT-6 Astra — daibond_alpha · 2026-10-30