GGUF models by matrixportalx
501 GGUF models quantized by matrixportalx on Hugging Face. Sizes run from 78M to 30.5B parameters. The longest trained context is 1024K tokens.
About matrixportalx on Hugging Face
matrixportalx has published 501 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Qwen. The most downloaded are Aya Expanse 8b, Gemma 3 4b It Abliterated and Layerskip Llama3.2 1B.
The quants matrixportalx publishes most often are Q4_K_M (246), Q4_0 (189), Q4_K_S (138) and Q5_K_M (78). Their Q4_K_M files range from 0.1 to 18.6 GB. Parameter counts run from 78M to 30.5B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has matrixportalx published?
501 models are listed here, mainly from the Llama, Gemma and Qwen families. The most downloaded is Aya Expanse 8b.
Which quants does matrixportalx publish?
The most common are Q4_K_M (246 models), Q4_0 (189 models), Q4_K_S (138 models) and Q5_K_M (78 models).