GGUF models by prabal123
36 GGUF models quantized by prabal123 on Hugging Face. Sizes run from 1.1B to 6.91B parameters. The longest trained context is 4K tokens.
About prabal123 on Hugging Face
prabal123 has published 36 GGUF models that ggufmodels.com tracks, across families such as Tinyllama, Llama and Openllama. The most downloaded are NR llama2 LogR Cust data q4 0 q4 k m, Nous research finetuned 1Epoch and Tinyllama 150 50 200 210epoch f32.
The quants prabal123 publishes most often are Q4_K_M (10), Q4_0 (3), Q4_1 (2) and Q3_K_M (2). Their Q4_K_M files range from 4.1 to 4.1 GB. Parameter counts run from 1.1B to 6.91B, and the longest trained context window is 4K tokens.
Frequently asked questions
What GGUF models has prabal123 published?
36 models are listed here, mainly from the Tinyllama, Llama and Openllama families. The most downloaded is NR llama2 LogR Cust data q4 0 q4 k m.
Which quants does prabal123 publish?
The most common are Q4_K_M (10 models), Q4_0 (3 models), Q4_1 (2 models) and Q3_K_M (2 models).