GGUF models by John1604
37 GGUF models quantized by John1604 on Hugging Face. Sizes run from 1.72B to 480B parameters. The longest trained context is 256K tokens.
About John1604 on Hugging Face
John1604 has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, John and DeepSeek. The most downloaded are Qwen3 Next 80B A3B Instruct, Qwen3 Coder 30B A3B Instruct and Qwen3 235B A22B Instruct 2507.
The quants John1604 publishes most often are Q4_K_M (36), Q3_K_M (36), Q6_K (35) and Q3_K_S (34). Their Q4_K_M files range from 1.1 to 290.1 GB. Parameter counts run from 1.72B to 480B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has John1604 published?
37 models are listed here, mainly from the Qwen, John and DeepSeek families. The most downloaded is Qwen3 Next 80B A3B Instruct.
Which quants does John1604 publish?
The most common are Q4_K_M (36 models), Q3_K_M (36 models), Q6_K (35 models) and Q3_K_S (34 models).