Gemma 4 26B A4B

Planned

google/gemma-4-26b-a4b-it

Gemma 4 26B-A4B is a sparse mixture-of-experts model from Google with roughly 4B active parameters, accepting text, image and audio input. It pairs multimodal breadth with the throughput of a far smaller dense model, and supports a 262K context window.

This model is on the roadmap but is not being served yet, so it will return model_not_found from the API. It appears here because we publish what we intend to run as openly as what we already do — the catalogue should tell you where the platform is going, not just where it is.