GGUF models by AIgotahole
38 GGUF models quantized by AIgotahole on Hugging Face. Sizes run from 4.62B to 26.1B parameters. The longest trained context is 1000K tokens.
About AIgotahole on Hugging Face
AIgotahole has published 38 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and GLM. The most downloaded are Qwen3 14B Abliterated, Olmo 3 1025 7B Stage1 Step1413814 and Huihui GLM 4.1V 9B Thinking Abliterated.
The quants AIgotahole publishes most often are Q5_K_M (12), Q4_K_S (11), Q4_K_M (8) and Q5_K_S (6). Their Q4_K_M files range from 6.2 to 15.8 GB. Parameter counts run from 4.62B to 26.1B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has AIgotahole published?
38 models are listed here, mainly from the Qwen, Gemma and GLM families. The most downloaded is Qwen3 14B Abliterated.
Which quants does AIgotahole publish?
The most common are Q5_K_M (12 models), Q4_K_S (11 models), Q4_K_M (8 models) and Q5_K_S (6 models).