GGUF models by liodon-ai
122 GGUF models quantized by liodon-ai on Hugging Face. Sizes run from 94M to 34.7B parameters. The longest trained context is 1024K tokens.
About liodon-ai on Hugging Face
liodon-ai has published 122 GGUF models that ggufmodels.com tracks, across families such as Qwen, Wav and Llama. The most downloaded are DeepHat V1 7B imatrix, Qwen3.6 35B A3B imatrix and DeepSeek R1 Distill Qwen 14B imatrix.
The quants liodon-ai publishes most often are Q8_0 (122), Q6_K (107), Q5_K_M (107) and Q4_K_M (107). Their Q4_K_M files range from 0.1 to 21.2 GB. Parameter counts run from 94M to 34.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has liodon-ai published?
122 models are listed here, mainly from the Qwen, Wav and Llama families. The most downloaded is DeepHat V1 7B imatrix.
Which quants does liodon-ai publish?
The most common are Q8_0 (122 models), Q6_K (107 models), Q5_K_M (107 models) and Q4_K_M (107 models).