I quanted this but can't get it to run, I tried on A100 which should work with Marlin kernel.

Please let me know if you are able to get it running and how, and I can update the docs

Eric Hartford

Downloads last month
3
Safetensors
Model size
133B params
Tensor type
F32
BF16
F8_E4M3
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support