Mistral AI/Text / LLM
Mistral's Leanstral 1.5 puts 119B in a lean MoE
The new Apache-2.0 mixture-of-experts model activates just 6B parameters per token, trading raw density for cheaper inference.
Company
Releases
The new Apache-2.0 mixture-of-experts model activates just 6B parameters per token, trading raw density for cheaper inference.
A 230-million-parameter model built to run on constrained hardware like Raspberry Pi and edge robotics.
The company, known for its powerful text models, has released its first open-source speech recognition system designed for real-time, multilingual transcription.
The French AI leader expands beyond large language models with a new, 4-billion-parameter model for generating multilingual speech.