GGUF models by DevQuasar-9
90 GGUF models quantized by DevQuasar-9 on Hugging Face. Sizes run from 620M to 70.6B parameters. The longest trained context is 1000K tokens.
About DevQuasar-9 on Hugging Face
DevQuasar-9 has published 90 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Granite. The most downloaded are DavidAU.Mistral MOE 4X7B Dark MultiVerse Uncensored Enhanced32 24B, Bigcode.Starcoder2 3b and Huihui ai.DeepSeekR1 QwQ SkyT1 32B Fusion 622.
The quants DevQuasar-9 publishes most often are Q5_K_M (90), Q4_K_M (90), Q3_K_M (90) and Q2_K (90). Their Q4_K_M files range from 0.4 to 42.5 GB. Parameter counts run from 620M to 70.6B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has DevQuasar-9 published?
90 models are listed here, mainly from the Qwen, Llama and Granite families. The most downloaded is DavidAU.Mistral MOE 4X7B Dark MultiVerse Uncensored Enhanced32 24B.
Which quants does DevQuasar-9 publish?
The most common are Q5_K_M (90 models), Q4_K_M (90 models), Q3_K_M (90 models) and Q2_K (90 models).