GGUF models by leafspark
36 GGUF models quantized by leafspark on Hugging Face. Sizes run from 121M to 218B parameters. The longest trained context is 1000K tokens.
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest36.5 GB
MI
Mistral Large 218B Instruct
Mistral · leafspark
Params218B
Context32K
Smallest0.0 GB
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest16.7 GB
MI
Mistral 7B Instruct v0.2
Mistral · leafspark
Params7.24B
Context32K
Q4_K_M4.4 GB
YI
Yi 1.5 9B Chat 16K Q2 K
Yi · leafspark
Params8.83B
Context16K
Smallest3.4 GB
YI
Yi 1.5 9B Chat 16K Q3 K S
Yi · leafspark
Params8.83B
Context16K
Smallest3.9 GB