merviscishes/Forgotten-Hubris-24B-v0.1

TEXT GENERATIONPricing:Input $0.7 / Cached $0.04 / Output $1.16Concurrent Unit Cost:2Model Size:24BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 12, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Forgotten-Hubris-24B-v0.1 by merviscishes is an experimental 24 billion parameter language model with a 32768-token context length, created via a Karcher Mean merge of eight 'heretic' and uncensored models. It is designed to produce unhinged output, including narratives with themes of violence and erotica, and is intended as a base for future long-form creative fiction writing. This model is explicitly noted for its experimental nature and potential to generate controversial content.

Loading preview...

Forgotten Hubris 24B v0.1: An Experimental Merge Model

merviscishes' Forgotten Hubris 24B v0.1 is an experimental 24 billion parameter language model, developed as a remix using the Karcher Mean merge method. This model was created by merging eight distinct base models, many of which are noted for being 'heretic' or uncensored variants, including:

Key Characteristics

  • Uncensored Output: The model is designed to produce

Finetunes
1 models