GGUF models by kainatq
34 GGUF models quantized by kainatq on Hugging Face. Sizes run from 7.24B to 14.8B parameters. The longest trained context is 1000K tokens.
About kainatq on Hugging Face
kainatq has published 34 GGUF models that ggufmodels.com tracks, across families such as Kpt, Azure and Quantum. The most downloaded are Kainaticulous Rp 7b, Ksong 1 12b_v1 and Kaiden Sakura Violet Square Azura crimson 12B Q4 K M.
The quants kainatq publishes most often are Q4_K_M (11), Q3_K_M (8), Q3_K_L (6) and Q6_K (4). Their Q4_K_M files range from 4.4 to 9.0 GB. Parameter counts run from 7.24B to 14.8B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has kainatq published?
34 models are listed here, mainly from the Kpt, Azure and Quantum families. The most downloaded is Kainaticulous Rp 7b.
Which quants does kainatq publish?
The most common are Q4_K_M (11 models), Q3_K_M (8 models), Q3_K_L (6 models) and Q6_K (4 models).