GGUF models by nold
43 GGUF models quantized by nold on Hugging Face. Sizes run from 1.35B to 46.7B parameters. The longest trained context is 512K tokens.
FU
FuseChat 7B VaRM
Fusechat · nold
Params7.24B
Context8K
Q4_K_M4.4 GB
ME
MediKAI
Medikai · nold
Params14.1B
Context8K
Q4_K_M8.7 GB
PH
phi 2
Phi · nold
Params2.78B
Context2K
Smallest1.9 GB
QW
firefly qwen1.5 en 7b
Qwen · nold
Params7.72B
Context32K
Q4_K_M4.8 GB
MA
Magicoder S DS 6.7B
Magicoder · nold
Params6.74B
Context16K
Q4_K_M4.1 GB
CR
CroissantLLMBase
Croissantllmbase · nold
Params1.35B
Context2K
Q4_K_M0.9 GB
EM
embryophagus
Embryophagus · nold
Params12.5B
Context32K
Q4_K_M7.5 GB
LW
LWM Text Chat 512K
Lwm · nold
Params6.74B
Context512K
Q4_K_M4.1 GB
MI
Prima Pastacles 7b
Mistral · nold
Params7.24B
Context8K
Q4_K_M4.4 GB
PH
phigment6 slerp
Phigment · nold
Params2.78B
Context2K
Q4_K_M1.7 GB
BE
34b beta
Beta · nold
Params34.4B
Context195K
Q4_K_M20.7 GB
PR
Prima LelantaclesV3 7b
Prima · nold
Params7.24B
Context32K
Q4_K_M4.4 GB
PH
Wiedervereinigung 7b dpo
Phoenix · nold
Params7.24B
Context32K
Q4_K_M4.4 GB