GGUF models by Naphula
92 GGUF models quantized by Naphula on Hugging Face. Sizes run from 3.88B to 107B parameters. The longest trained context is 1048K tokens.
DE
DeepHermes3 24B textonly Q6 K
Deephermes · Naphula
Params23.6B
Context32K
Smallest19.3 GB
GO
Golem 70B v1a
Golem · Naphula
Params70.6B
Context8K
Q4_K_M43.9 GB