Gemma 4 goes Apache 2.0, spanning edge-sized models to a 31B dense model
Google DeepMind released Gemma 4 in four sizes (effective 2B and 4B edge models, a 26B mixture-of-experts and a 31B dense model) under the Apache 2.0 license. The models support function calling, structured output, vision and audio, with context windows of 128K to 256K tokens. For developers, the switch to a standard permissive license removes a common legal hurdle to shipping Gemma in commercial products.
Read the full story at Google ↗Like, save or discuss on Buzz
