bf16 is now broken. Latest llama.cpp
#6
by
GeorgyGUF
- opened
gguf_init_from_file: failed to open GGUF file 'gemma-3-4b-it-BF16.gguf'
llama_model_load: error loading model: llama_model_loader: failed to load model from gemma-3-4b-it-BF16.gguf
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model 'gemma-3-4b-it-BF16.gguf'
main: error: unable to load model
https://huggingface.co/Mungert/gemma-3-4b-it-gguf/blob/main/google_gemma-3-4b-it-bf16.gguf has different sha256 hash
GeorgyGUF
changed discussion status to
closed
GeorgyGUF
changed discussion status to
open
and it is fresh and working