GGUF models by majentik
129 GGUF models quantized by majentik on Hugging Face. Sizes run from 475M to 284B parameters. The longest trained context is 1024K tokens.
About majentik on Hugging Face
majentik has published 129 GGUF models that ggufmodels.com tracks, across families such as Gemma, Nemotron and Qwen. The most downloaded are gemma 4 12B it TurboQuant GGUF IQ4 XS, Qwen3 Embedding 0.6B GGUF Q8 0 and gemma 4 26B A4B it RotorQuant GGUF Q4 K M.
The quants majentik publishes most often are Q4_K_M (24), Q8_0 (23), Q5_K_M (23) and IQ4_XS (23). Their Q4_K_M files range from 0.4 to 86.1 GB. Parameter counts run from 475M to 284B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has majentik published?
129 models are listed here, mainly from the Gemma, Nemotron and Qwen families. The most downloaded is gemma 4 12B it TurboQuant GGUF IQ4 XS.
Which quants does majentik publish?
The most common are Q4_K_M (24 models), Q8_0 (23 models), Q5_K_M (23 models) and IQ4_XS (23 models).