This repo includes .gguf built for HuggingFace/Candle. They will not work with llama.cpp.

This model should be used with the Config config_chat_ml.

Refer to the original repo for more details.

Downloads last month
78
GGUF
Model size
7B params
Architecture
undefined
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for DanielClough/Candle_MistralLite

Quantizations
2 models