GGUF models by Ramikan-BR
77 GGUF models quantized by Ramikan-BR on Hugging Face. Sizes run from 494M to 8.03B parameters. The longest trained context is 128K tokens.
TI
tinyllama PY CODER bnb 4bit lora 4k Q8 0 v3
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest1.2 GB
TI
TiamaPY-v35
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
TiamaPY-v36
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
TiamaPY-v43
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
TiamaPY-v37
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
tinyllama-coder-py-4bit-v2
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
TI
TiamaPY-v30
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Q4_K_M0.7 GB
QW
Qwen2 0.5B v12
Qwen · Ramikan-BR
Params494M
Context128K
Smallest1.0 GB
TI
TiamaPY-v38
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
TiamaPY-v41
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest2.2 GB
TI
TiamaPY-1.1B-v24
Tiamapy · Ramikan-BR
Params1.1B
Context4K
Smallest1.2 GB
TI
tinyllama-coder-py-4bit-v6
Tinyllama · Ramikan-BR
Params1.1B
Context4K
Smallest1.2 GB
QW
Qwen2 0.5B v20 Q8 0
Qwen · Ramikan-BR
Params494M
Context128K
Smallest0.5 GB
MI
Mis3 7b v1 Q4 K M
Mis · Ramikan-BR
Params7.25B
Context32K
Q4_K_M4.4 GB
MI
P3 mini v3 Q8 0
Mini · Ramikan-BR
Params3.82B
Context4K
Smallest4.1 GB
CO
Codama-8b-v0
Codama · Ramikan-BR
Params8.03B
Context8K
Q4_K_M4.9 GB
MI
P3 mini v6 Q8 0
Mini · Ramikan-BR
Params3.82B
Context4K
Smallest4.1 GB