GGUF models by redponike
45 GGUF models quantized by redponike on Hugging Face. Sizes run from 1.72B to 229B parameters. The longest trained context is 256K tokens.
About redponike on Hugging Face
redponike has published 45 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Ling. The most downloaded are Qwen3 VL 30B A3B Thinking, Qwen3 VL 4B Instruct and Ring Flash 2.0.
The quants redponike publishes most often are Q4_K_M (40), Q3_K_M (39), Q4_K_S (38) and Q3_K_S (38). Their Q4_K_M files range from 1.1 to 138.3 GB. Parameter counts run from 1.72B to 229B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has redponike published?
45 models are listed here, mainly from the Qwen, Llama and Ling families. The most downloaded is Qwen3 VL 30B A3B Thinking.
Which quants does redponike publish?
The most common are Q4_K_M (40 models), Q3_K_M (39 models), Q4_K_S (38 models) and Q3_K_S (38 models).