Q4_K_M quantized derivatives of Google's official TranslateGemma weights, re-hosted here for use as a bundled, fully-local translation engine (run via llama.cpp).

These files are quantized (Q4_K_M) from the official google/translategemma-* weights. They are modified (quantized) copies of the original model, not the original weights. The GGUF conversions were obtained from the community mradermacher static-quant repositories (which document the same official Google source) and re-hosted here unchanged.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms