GGUF models by bau0221
39 GGUF models quantized by bau0221 on Hugging Face. Sizes run from 1.24B to 3.82B parameters. The longest trained context is 128K tokens.
MO
model 1204
Model · bau0221
Params1.24B
Context128K
Smallest1.3 GB
HL
HLI 0115
Hli · bau0221
Params1.24B
Context128K
Smallest1.3 GB
LL
model 1212
Llama · bau0221
Params1.24B
Context128K
Smallest1.3 GB
HL
HLI 0114
Hli · bau0221
Params1.24B
Context128K
Smallest1.3 GB
MO
1112 model 2
Model · bau0221
Params1.24B
Context128K
Smallest1.3 GB
HL
HLI 0115GGUF 2
Hli · bau0221
Params1.24B
Context128K
Smallest1.3 GB
LL
1113 model llama
Llama · bau0221
Params1.24B
Context128K
Smallest1.3 GB
HL
HLI 0107
Hli · bau0221
Params1.24B
Context128K
Smallest1.3 GB
MO
model
Model · bau0221
Params1.24B
Context128K
Smallest1.3 GB