GGUF models by jnjj
35 GGUF models quantized by jnjj on Hugging Face. Sizes run from 4M to 3.88B parameters. The longest trained context is 1280000K tokens.
About jnjj on Hugging Face
jnjj has published 35 GGUF models that ggufmodels.com tracks, across families such as Gemma, Qwen and Model. The most downloaded are xd v2, Gemma 3 4b It Qat Int4 Quantized Inference Unrestricted Weights Only Sf and Gemma 3 1b It Qat Q4_0 Quantized Inference Extreme Shrinkage Sf.
The quants jnjj publishes most often are Q2_K (18), Q3_K_L (6), Q8_0 (4) and Q4_0 (3). Their Q4_K_M files range from 0.0 to 0.0 GB. Parameter counts run from 4M to 3.88B, and the longest trained context window is 1280000K tokens.
Frequently asked questions
What GGUF models has jnjj published?
35 models are listed here, mainly from the Gemma, Qwen and Model families. The most downloaded is xd v2.
Which quants does jnjj publish?
The most common are Q2_K (18 models), Q3_K_L (6 models), Q8_0 (4 models) and Q4_0 (3 models).