OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-DEEP

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 25, 2026License:mitArchitecture:Transformer0.0K Open Weights Featherless Exclusive Cold

OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-DEEP is a 9 billion parameter language model, derived from OliviaRossi/MiMo-Ornith-9B-AGSI, specifically engineered for uncensored creative writing, dark fiction, investigative deep-research, and unfiltered information summarization. It features a 32768 token context length and has been modified using Abliterix to nullify refusals and prevent self-censorship, offering full narrative plasticity. This model is optimized for use cases requiring unrestricted content generation and deep research without moralizing disclaimers.

Loading preview...

Overview

OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-DEEP is a 9 billion parameter model based on OliviaRossi/MiMo-Ornith-9B-AGSI, specifically designed for uncensored creative writing, dark fiction, investigative deep-research, and unfiltered information summarization. It has been extensively modified to remove content restrictions and self-censorship.

Key Capabilities

  • Full Decensorship: Engineered to eliminate refusals and moralizing disclaimers, providing unrestricted content generation.
  • Narrative Plasticity: Calibrated to allow full creative freedom, preventing self-censorship in writing tasks.
  • Deep Research: Optimized for complex research queries and unfiltered information summarization.
  • Reasoning Support: Preserves multi-tier reasoning effort controls (none, low, medium, high, max) and zero-loss KV caching.

Good For

  • Generating uncensored creative writing and dark fiction.
  • Performing investigative deep-research without content filtering.
  • Summarizing information without moralizing or preachy disclaimers.
  • Applications requiring a language model with full narrative control and no inherent content restrictions.