cortexist/little-gemma

lightweight, standalone C++ inference engine for Google's Gemma models.

Gemma 3 pure inference in C

Gemma 4 E2B inference in pure C

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

LLM inference in C/C++

The official PyTorch implementation of Google's Gemma models

Experimental llama.cpp fork for inference research and development

Experimental Godot 4.7 project running Gemma 4 inference entirely in GDScript and Vulkan compute shaders