I got Gemma 4 running directly inside Godot using only GDScript and Vulkan compute shaders
Summary
A developer successfully integrated Gemma 4 AI model into the Godot game engine using only GDScript and Vulkan compute shaders, enabling local AI inference within games.
Similar Articles
Gemma 4 E2B running in-browser at 255 tok/s using WebGPU kernels written by Fable 5
Gemma 4 is demonstrated running in-browser via WebGPU at 255 tokens per second, using kernels generated by Fable 5, showcasing efficient on-device inference.
@googlegemma: Gemma 4 now works on-device using React Native! You can now run Gemma 4 fully offline in your cross-platform apps with …
Gemma 4 can now run fully offline on-device using React Native, with local hardware acceleration via Vulkan on Android and MLX on Apple Silicon, enabling vision and tool-use capabilities like reading a flyer and scheduling events entirely on-device.
You don't need a GPU to run gemma-4-26B-A4B
The author demonstrates that the Gemma-4-26B-A4B model runs efficiently on a CPU-only system using Koboldcpp, achieving 7 tokens per second on an old desktop, suggesting that powerful GPUs may not be necessary for local LLM inference.
Android Studios native Gemma 4 runs on llama.cpp
Android Studio now natively supports running the Gemma 4 AI model using llama.cpp, with features like multi-GPU support and a 128k context length.
Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon with no GPU
A developer successfully runs Google's Gemma 4 26B mixture-of-experts model at about 5 tokens per second on a 13-year-old dual Xeon server without a GPU, using a modified version of ik_llama.cpp that works without AVX2 instructions.