ggml-org

/

gemma-3-4b-it-GGUF

like 42

Follow

ggml.ai 931

According to ggml-org documentation at:
https://github.com/ggml-org/llama.cpp/blob/master/docs/multimodal.md
We instructed to specify a mmproj file to enable the vision model:

"Use -m model.gguf option with --mmproj file.gguf to specify text and multimodal projector respectively"

But no mmproj file is supplied with this model.

Please clarify what a user needs to do to get vision working.

Thanks!