Mistral publishes Mistral Large 3 675B Eagle speculative decoding model
Mistral AI released Mistral-Large-3-675B-Instruct-2512-Eagle, a 675B parameter instruct model variant, on Hugging Face under Apache 2.0. The Eagle suffix typically indicates a speculative decoding draft model designed to accelerate inference of the base model. Supports 11 languages.
PUBLISHED2025-11-10
OBSERVED2026-08-11
AGE9mo
SOURCES1
- Model published at
mistralai/Mistral-Large-3-675B-Instruct-2512-Eagle - Library: vllm
- Languages: en, fr, es, de, it, pt, nl, zh, ja, ko, ar
- License: Apache 2.0
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.