GGUF models by dhruvsangani
35 GGUF models quantized by dhruvsangani on Hugging Face. Sizes run from 1.1B to 8.03B parameters. The longest trained context is 128K tokens.
About dhruvsangani on Hugging Face
dhruvsangani has published 35 GGUF models that ggufmodels.com tracks, across families such as Featgpt, Featbot and Feat. The most downloaded are Meta Llma 3.2 3B Instruct Paul Graham GGUF, Sentiment Analysis Of Banking Dataset GGUF and Llama 3.2 1B Instruct Banking_Customer_Support GGUF.
The quants dhruvsangani publishes most often are Q4_K_M (35). Their Q4_K_M files range from 0.7 to 4.9 GB. Parameter counts run from 1.1B to 8.03B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has dhruvsangani published?
35 models are listed here, mainly from the Featgpt, Featbot and Feat families. The most downloaded is Meta Llma 3.2 3B Instruct Paul Graham GGUF.
Which quants does dhruvsangani publish?
The most common are Q4_K_M (35 models).