GGUF models by wop
34 GGUF models quantized by wop on Hugging Face. Sizes run from 18M to 4.21B parameters. The longest trained context is 256K tokens.
QU
Quble_Test_Model_v1_Pretrain
Quble · wop
Params163M
Context1K
Smallest0.1 GB
QU
Quble_Test_Model_v1_Pretrain
Quble · wop
Params163M
Context1K
Smallest0.1 GB
QU
Quble_Test_Model_v1_Pretrain
Quble · wop
Params163M
Context1K
Smallest0.2 GB
AR
arptron_beta_0
Arptron · wop
Params163M
Context1K
Q4_K_M0.1 GB