GGUF models by Jackrong
66 GGUF models quantized by Jackrong on Hugging Face. Sizes run from 334M to 35B parameters. The longest trained context is 256K tokens.
About Jackrong on Hugging Face
Jackrong has published 66 GGUF models that ggufmodels.com tracks, across families such as Qwen, Qwopus and Llama. The most downloaded are Qwopus3.8 27B Flash V2, Qwopus3.6 35B A3B Coder and Qwopus3.6 27B Coder Compat MTP.
The quants Jackrong publishes most often are Q4_K_M (62), Q8_0 (59), Q6_K (48) and Q5_K_M (48). Their Q4_K_M files range from 0.4 to 21.7 GB. Parameter counts run from 334M to 35B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has Jackrong published?
66 models are listed here, mainly from the Qwen, Qwopus and Llama families. The most downloaded is Qwopus3.8 27B Flash V2.
Which quants does Jackrong publish?
The most common are Q4_K_M (62 models), Q8_0 (59 models), Q6_K (48 models) and Q5_K_M (48 models).