This model is just a test. It's really just an attempt to merge Morax and Pantheon. But at 0.5 Morax and 0.5 Pantheon, Morax is far too dominant. I'm working on a better version.

Downloads last month
7
GGUF
Model size
24B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ewald1976/Pantorax-24b-v0.5-f16.gguf

Collection including ewald1976/Pantorax-24b-v0.5-f16.gguf