GGUF models by devisri050
93 GGUF models quantized by devisri050 on Hugging Face. Sizes run from 23M to 14.8B parameters. The longest trained context is 128K tokens.
About devisri050 on Hugging Face
devisri050 has published 93 GGUF models that ggufmodels.com tracks, across families such as Qwen, Tinyllama and Mistral. The most downloaded are Stable Code 3b, Falcon3 10B Base and InternVL3 14B.
The quants devisri050 publishes most often are Q8_0 (28), Q4_0 (24), Q4_K_S (21) and Q4_K_M (20). Their Q4_K_M files range from 0.0 to 9.0 GB. Parameter counts run from 23M to 14.8B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has devisri050 published?
93 models are listed here, mainly from the Qwen, Tinyllama and Mistral families. The most downloaded is Stable Code 3b.
Which quants does devisri050 publish?
The most common are Q8_0 (28 models), Q4_0 (24 models), Q4_K_S (21 models) and Q4_K_M (20 models).