A collection of GGUF-quantized files for various test versions, merges, and experimental checkpoints related to Google's Gemma 4 models. Created by ToastyPigeon, these files allow users to run the models locally with tools such as llama.cpp, LM Studio, or Ollama. The repository includes different quantization levels (Q4, Q6, Q8) and several merged variants for testing and evaluation purposes.
Gemma4 Test GGUFs is a Foundation models & chat project. It focuses on providing ready-to-use quantized GGUF files of experimental Gemma 4 models and merges for local LLM experimentation. It is built as an open-source project for developers. The project is open source (Open Source). Gemma4 Test GGUFs is available on the command line.
Behind Gemma4 Test GGUFs is ToastyPigeon, and it first shipped in 2025. It operates in a well-populated space: PulseGate tracks 6 similar projects. Among its 3 catalogued features are GGUF format, multiple quantization levels, and model merges.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do