GGUF models by prabal123

36 GGUF models quantized by prabal123 on Hugging Face. Sizes run from 1.1B to 6.91B parameters. The longest trained context is 4K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Open_Llama_3B
Llama · prabal123
Params3.43B
Context2K
Smallest3.6 GB
GGUF
LL
NR Llama2 LogR Cus data q4 k m
Llama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Meta Llama2 llamadataformat 30Epoch
Llama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OP
Openllama 50Epoch
Openllama · prabal123
Params3.43B
Context2K
Smallest3.6 GB
GGUF
ME
Metallama Noaccountnum 6EPOCH 1
Metallama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OP
openllama 8epoch graphofloss
Openllama · prabal123
Params3.43B
Context2K
Smallest3.6 GB
GGUF

Keep browsing