GGUF models by Kondara
52 GGUF models quantized by Kondara on Hugging Face. Sizes run from 1.23B to 19.9B parameters. The longest trained context is 1000K tokens.
About Kondara on Hugging Face
Kondara has published 52 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Qwen. The most downloaded are Qwen2.5 Coder 7B Instruct, DeepSeek R1 Distill Qwen 7B and Llama 3.2 3B Instruct.
The quants Kondara publishes most often are Q4_K_M (45), Q8_0 (5) and Q6_K (2). Their Q4_K_M files range from 0.8 to 12.0 GB. Parameter counts run from 1.23B to 19.9B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has Kondara published?
52 models are listed here, mainly from the Llama, Gemma and Qwen families. The most downloaded is Qwen2.5 Coder 7B Instruct.
Which quants does Kondara publish?
The most common are Q4_K_M (45 models), Q8_0 (5 models) and Q6_K (2 models).