Loading page…
Cookies keep FreeInd working. Optional analytics require your permission; ads for free accounts are served by Google, which shows its own consent message where required. Read our cookie policy.
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at
FreeInd is an independent platform and is not affiliated with, endorsed by, or sponsored by Google or the creators or owners of Google: Gemma 4 26B A4B. The Google name and mark appear solely to identify the integrations available on this platform.
The generation modes and formats Google: Gemma 4 26B A4B supports on this platform.
Other live Google models on the platform.
Continue browsing the catalog by original model maker.
