GGUF models by EloyOn
40 GGUF models quantized by EloyOn on Hugging Face. Sizes run from 4.51B to 36.2B parameters. The longest trained context is 1000K tokens.
About EloyOn on Hugging Face
EloyOn has published 40 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and Impish. The most downloaded are Impish_Bloodmoon_12B_Abliterated, Gemma 3 27b It Abliterated and M3.2 24B Loki V1.3.
The quants EloyOn publishes most often are Q5_0 (35), Q4_K_M (2), Q4_0 (2) and Q4_K_S (1). Their Q4_K_M files range from 4.9 to 7.5 GB. Parameter counts run from 4.51B to 36.2B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has EloyOn published?
40 models are listed here, mainly from the Qwen, Phi and Impish families. The most downloaded is Impish_Bloodmoon_12B_Abliterated.
Which quants does EloyOn publish?
The most common are Q5_0 (35 models), Q4_K_M (2 models), Q4_0 (2 models) and Q4_K_S (1 models).