Naphula/GhostFace-24B-v1
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Mar 4, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Naphula/GhostFace-24B-v1 is a 24 billion parameter Mistral-based merged language model, created by Naphula, utilizing a custom 'scream' merging method. This model integrates multiple Mistral 24B merges and finetunes, resulting in a model that can produce narratives and roleplay with violent and graphic erotic content. It is designed for use cases requiring intelligent responses, particularly when paired with specific chat templates like Mistral Tekken.

Loading preview...