Open-source (Apache 2.0)
Mixtral — specs and what replaced it
Mixture of Experts model with 8 experts per MLP, total of 45B parameters
- Modalities
- Text
Overview
What Mixtral is good at
This model is retired from this directory. It is superseded by a current model from the same provider. Note that unlike Anthropic, this provider does not publish an official replacement mapping — the successor named here is Avinashi AI's judgement, based on matching provider and tier, not the provider's own recommendation.
Not sure Mixtral fits your workload?
We'll size the right model for your use case and give you a real cost estimate. One free call, no slides.
Talk to us