GGUF models by LiquidAI
55 GGUF models quantized by LiquidAI on Hugging Face. Sizes run from 190M to 24B parameters. The longest trained context is 256K tokens.
About LiquidAI on Hugging Face
LiquidAI has published 55 GGUF models that ggufmodels.com tracks, across families such as Lfm and Omni. The most downloaded are LFM2.5 2.6B, LFM2.5 Audio 1.5B JP and LFM2.5 1.2B Instruct.
The quants LiquidAI publishes most often are F16 (55), Q8_0 (53), Q4_0 (45) and Q4_K_M (43). Their Q4_K_M files range from 0.2 to 14.5 GB. Parameter counts run from 190M to 24B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has LiquidAI published?
55 models are listed here, mainly from the Lfm and Omni families. The most downloaded is LFM2.5 2.6B.
Which quants does LiquidAI publish?
The most common are F16 (55 models), Q8_0 (53 models), Q4_0 (45 models) and Q4_K_M (43 models).