GGUF models by prithivMLmods
599 GGUF models quantized by prithivMLmods on Hugging Face. Sizes run from 135M to 180B parameters. The longest trained context is 1024K tokens.
About prithivMLmods on Hugging Face
prithivMLmods has published 599 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are Qwen Image 2.1 PE I2I, Qwen Image 2.1 PE T2I and JEV 27B VL.
The quants prithivMLmods publishes most often are Q4_K_M (469), Q5_K_M (458), Q8_0 (449) and BF16 (439). Their Q4_K_M files range from 0.1 to 75.8 GB. Parameter counts run from 135M to 180B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has prithivMLmods published?
599 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is Qwen Image 2.1 PE I2I.
Which quants does prithivMLmods publish?
The most common are Q4_K_M (469 models), Q5_K_M (458 models), Q8_0 (449 models) and BF16 (439 models).