GGUF models by win10
97 GGUF models quantized by win10 on Hugging Face. Sizes run from 21M to 40.6B parameters. The longest trained context is 1024K tokens.
MI
Miscii 14b 1225
Miscii · win10
Params14.8B
Context128K
Smallest15.7 GB
MI
miscii Virtuoso Small Q8 0
Miscii · win10
Params14.8B
Context128K
Smallest15.7 GB
PR
24B MS PRO V0.01 Q6 K
Pro · win10
Params23.6B
Context32K
Smallest19.3 GB
PH
phi 3.5 Sakura Yuzu Q8 0
Phi · win10
Params3.82B
Context128K
Smallest4.1 GB
ME
mergekit model stock nvgaatl Q8 0
Mergekit · win10
Params14.8B
Context986K
Smallest15.7 GB
LL
ArliAI RPMax v1.3 merge llama3 8B Q8 0
Llama · win10
Params8.03B
Context8K
Smallest8.5 GB
NE
nemolita 21b Q8 0
Nemolita · win10
Params20.4B
Context1000K
Smallest21.7 GB