Mistral Large 4 Open Weights: Running a 1T MoE Locally Without the Cloud Tax
This story is from 2026-10-30. It is preserved in the archive; the latest stories are on the live feed.
Mistral just dropped the open weights for Large 4 (“Le Chonk”), a 1-trillion-parameter multimodal Mixture-of-Experts model with roughly 49–52 billion active parameters per token and a 1M-token context. Trained from scratch on European Grace Blackwell clusters, it leads open-weight coding-agent and…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-30 09:15 · DEV Community — AI
Mistral Large 4 Open Weights: Running a 1T MoE Locally Without the Cloud Tax