GGUF models by DevQuasar-10
42 GGUF models quantized by DevQuasar-10 on Hugging Face. Sizes run from 10M to 70.6B parameters. The longest trained context is 128K tokens.
About DevQuasar-10 on Hugging Face
DevQuasar-10 has published 42 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Granite. The most downloaded are Google.Gemma 3 27b It, Openai Community.Gpt2 Xl and Llama 3.1 Nemotron Nano 8B v1.
The quants DevQuasar-10 publishes most often are Q5_K_M (42), Q4_K_M (42), Q3_K_M (42) and Q2_K (42). Their Q4_K_M files range from 0.0 to 42.5 GB. Parameter counts run from 10M to 70.6B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has DevQuasar-10 published?
42 models are listed here, mainly from the Llama, Gemma and Granite families. The most downloaded is Google.Gemma 3 27b It.
Which quants does DevQuasar-10 publish?
The most common are Q5_K_M (42 models), Q4_K_M (42 models), Q3_K_M (42 models) and Q2_K (42 models).