Sicarius-Prototyping/Nammu_72B_Base

Hugging Face
TEXT GENERATIONConcurrency Cost:4Model Size:72.7BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 12, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

Nammu_72B_Base by Sicarius-Prototyping is a 72.7 billion parameter Qwen-based language model with a 32768 token context length. This base model is designed to be uncensored and intelligent, serving as a foundation for further development and specialized applications.

Loading preview...

Overview

Sicarius-Prototyping's Nammu_72B_Base is a 72.7 billion parameter language model built upon the Qwen architecture. Released as a work in progress, this model is noted for its uncensored nature and intelligent capabilities, intended as a foundational component for future projects.

Key Characteristics

  • Architecture: Based on the Qwen 72B model.
  • Parameters: 72.7 billion parameters.
  • Context Length: Supports a context window of 32768 tokens.
  • Censorship: Designed to be uncensored.
  • Development Stage: Currently a work in progress, released due to community interest.

Intended Use

This model is primarily intended as a base for further development and specialized applications. Its uncensored nature suggests potential use cases where unrestricted language generation is desired.

Finetunes
1 models