GGUF models by Azure99
40 GGUF models quantized by Azure99 on Hugging Face. Sizes run from 1.84B to 36.2B parameters. The longest trained context is 512K tokens.
BL
Blossom V6.1 14B
Blossom · Azure99
Params14.8B
Context32K
Q4_K_M9.0 GB
BL
blossom v5 34b
Blossom · Azure99
Params34.4B
Context4K
Q4_K_M20.7 GB
BL
Blossom V6 7B
Blossom · Azure99
Params7.62B
Context128K
Q4_K_M4.7 GB
MI
blossom v4 mistral 7b
Mistral · Azure99
Params7.24B
Context32K
Q4_K_M4.4 GB
GL
Blossom V6.1 GLM 32B
GLM · Azure99
Params32.6B
Context32K
Q4_K_M19.7 GB
BL
blossom v5 9b
Blossom · Azure99
Params8.83B
Context4K
Q4_K_M5.3 GB
BL
Blossom V6 14B
Blossom · Azure99
Params14.8B
Context128K
Q4_K_M9.0 GB
BL
blossom v5 14b
Blossom · Azure99
Params14.2B
Context32K
Q4_K_M9.2 GB
BL
blossom v4 baichuan2 7b
Blossom · Azure99
Params7.51B
Context4K
Q4_K_M4.6 GB
BL
Blossom V6 32B
Blossom · Azure99
Params32.8B
Context128K
Q4_K_M19.9 GB