Name and Version Yeah, title + logs basically. Verified correct files were downloaded with sha and I just can't load em and I don't get any errors. Version: $ llama-cli.exe --version ggml_cuda_init ...

Expected Behavior I am trying to load the multimodal model bartowski/google_gemma-3-4b-it-qat-GGUF using the Llama.from_pretrained method. The script is configured to use the Llama3VisionAlphaChatH ...