GGUF models by student-abdullah
34 GGUF models quantized by student-abdullah on Hugging Face. Sizes run from 494M to 8.03B parameters. The longest trained context is 128K tokens.
About student-abdullah on Hugging Face
student-abdullah has published 34 GGUF models that ggufmodels.com tracks, across families such as Llama and Qwen. The most downloaded are Llama3.2 Med Dataset Finetuning 01 10 32 bit, Llama3.1 medicine 13Sep 8bit and llama3.1 medicine fine tuned 8bits.
The quants student-abdullah publishes most often are F32 (13), Q8_0 (10), F16 (10) and Q5_K_M (4). Parameter counts run from 494M to 8.03B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has student-abdullah published?
34 models are listed here, mainly from the Llama and Qwen families. The most downloaded is Llama3.2 Med Dataset Finetuning 01 10 32 bit.
Which quants does student-abdullah publish?
The most common are F32 (13 models), Q8_0 (10 models), F16 (10 models) and Q5_K_M (4 models).