React Native ExecuTorch now runs Gemma 4 (Vulkan and MLX accelerated)
The react-native-executorch project has successfully integrated Gemma 4, enabling offline execution of the model within React Native applications. This integration leverages GPU acceleration through the Vulkan delegate on Android devices and the MLX delegate on Apple Silicon hardware. A demo application showcasing this functionality is available on GitHub. AI
IMPACT Enables offline, on-device execution of Gemma 4 within mobile applications, expanding its accessibility and use cases.