Model request
#251
by
drmcbride
- opened
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
I heard hui hui is making a abliterated version soon so you should run this so we have a baseline.
Also https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
I want to see how bad it is.
Grumble.
"Error loading model: Failed to load model from file"
llama-cpp-python hasn't been updated since March 12. I'll definitely be switching to something like vllm the next time I remake the leaderboard.