GGUF models by Alcoft
44 GGUF models quantized by Alcoft on Hugging Face. Sizes run from 135M to 27.3B parameters. The longest trained context is 256K tokens.
About Alcoft on Hugging Face
Alcoft has published 44 GGUF models that ggufmodels.com tracks, across families such as Qwen, SmolLM and Granite. The most downloaded are dnotitia_Smoothie Qwen3 14B, dnotitia_Smoothie Qwen3 4B and dnotitia_Smoothie Qwen3 0.6B.
The quants Alcoft publishes most often are Q6_K (44), Q5_K_M (44), Q4_K_S (44) and Q8_0 (43). Their Q4_K_M files range from 0.1 to 9.0 GB. Parameter counts run from 135M to 27.3B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has Alcoft published?
44 models are listed here, mainly from the Qwen, SmolLM and Granite families. The most downloaded is dnotitia_Smoothie Qwen3 14B.
Which quants does Alcoft publish?
The most common are Q6_K (44 models), Q5_K_M (44 models), Q4_K_S (44 models) and Q8_0 (43 models).