GGUF models by abubakar-muhammad
37 GGUF models quantized by abubakar-muhammad on Hugging Face. Sizes run from 135M to 3.21B parameters. The longest trained context is 128K tokens.
About abubakar-muhammad on Hugging Face
abubakar-muhammad has published 37 GGUF models that ggufmodels.com tracks, across families such as SmolLM, Llama and Gemma. The most downloaded are Llama 3.2 3b Paper Counterspeech Model Q4_K_M, Gemma 2 2b Paper Counterspeech Model Q4_K_M and counterspeech model 3b test finetuned llama 3.2 16 bit.
The quants abubakar-muhammad publishes most often are Q4_K_M (13), F16 (13), Q8_0 (12) and Q5_K_M (1). Their Q4_K_M files range from 0.1 to 2.0 GB. Parameter counts run from 135M to 3.21B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has abubakar-muhammad published?
37 models are listed here, mainly from the SmolLM, Llama and Gemma families. The most downloaded is Llama 3.2 3b Paper Counterspeech Model Q4_K_M.
Which quants does abubakar-muhammad publish?
The most common are Q4_K_M (13 models), F16 (13 models), Q8_0 (12 models) and Q5_K_M (1 models).