GGUF models by vantagewithai
51 GGUF models quantized by vantagewithai on Hugging Face. Sizes run from 2.1B to 33.1B parameters. The longest trained context is 256K tokens.
About vantagewithai on Hugging Face
vantagewithai has published 51 GGUF models that ggufmodels.com tracks, across families such as Ltx, Wan and Qwen. The most downloaded are Krea 2 Turbo, LongCat Video Avatar 1.5 GGUF ComfyUI and Sulphur 2 Base.
The quants vantagewithai publishes most often are Q6_K (50), Q5_K_M (50), Q4_K_M (50) and Q8_0 (49). Their Q4_K_M files range from 0.2 to 19.9 GB. Parameter counts run from 2.1B to 33.1B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has vantagewithai published?
51 models are listed here, mainly from the Ltx, Wan and Qwen families. The most downloaded is Krea 2 Turbo.
Which quants does vantagewithai publish?
The most common are Q6_K (50 models), Q5_K_M (50 models), Q4_K_M (50 models) and Q8_0 (49 models).