GGUF models by taronaeo
34 GGUF models quantized by taronaeo on Hugging Face. Sizes run from 23M to 32.2B parameters. The longest trained context is 1024K tokens.
About taronaeo on Hugging Face
taronaeo has published 34 GGUF models that ggufmodels.com tracks, across families such as Granite, Qwen and Llama. The most downloaded are Granite 4.2 3B BE, Granite 4.0 1B BE and Granite 4.0 350M BE.
The quants taronaeo publishes most often are Q8_0 (33), Q6_K (32), Q4_K_S (32) and Q4_K_M (32). Their Q4_K_M files range from 0.0 to 19.5 GB. Parameter counts run from 23M to 32.2B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has taronaeo published?
34 models are listed here, mainly from the Granite, Qwen and Llama families. The most downloaded is Granite 4.2 3B BE.
Which quants does taronaeo publish?
The most common are Q8_0 (33 models), Q6_K (32 models), Q4_K_S (32 models) and Q4_K_M (32 models).