GGUF models by ukung
43 GGUF models quantized by ukung on Hugging Face. Sizes run from 135M to 14B parameters. The longest trained context is 256K tokens.
QW
qwen3 4b function calling finetuned
Qwen · ukung
Params4.02B
Context256K
Smallest4.3 GB
QW
qwen3 4B finetune sintesis dataset
Qwen · ukung
Params4.02B
Context40K
Smallest4.3 GB
SM
smollamdk 3
Smollamdk · ukung
Params135M
Context8K
Smallest0.1 GB
GE
Coba Gemma Code Finetune
Gemma · ukung
Params2.51B
Context8K
Q4_K_M1.6 GB
QW
qwen3 4B finetune sintesis dataset v3
Qwen · ukung
Params4.02B
Context256K
Smallest4.3 GB
NU
Nusantara 2.7b Indo Chat
Nusantara · ukung
Params2.65B
Context8K
Q4_K_M1.7 GB
CO
collections model
Collections · ukung
Params1.72B
Context256K
Smallest0.5 GB
PO
Power WizardLM 2 13b
Power · ukung
Params12.5B
Context32K
Smallest7.1 GB
UK
KL000012
Ukung · ukung
Params2.61B
Context8K
Q4_K_M1.7 GB
QW
Qwen3 4B Instruct 2507 Enhanced
Qwen · ukung
Params4.02B
Context256K
Smallest4.3 GB
YI
Yi-1.5-9B-Chat
Yi · ukung
Params8.83B
Context4K
Q4_K_M5.3 GB
TI
TinyMistral 248M Chat v2
Tinymistral · ukung
Params248M
Context2K
Q4_K_M0.2 GB
MI
Mistral INDO 7B
Mistral · ukung
Params7.24B
Context32K
Q4_K_M4.4 GB