llama : Add Gemma 3 support (+ experimental vision capability) by ngxson · Pull Request #12343 · ggml-org/llama.cpp

Model info Official model page: https://ai.google.dev/gemma/docs/core Pre-quantized GGUF: https://huggingface.co/collections/ggml-org/gemma-3-67d126315ac810df1ad9e913 Available sizes: 1B, 4B, 12B,...