unsloth/Hermes-4-70B
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:32kPublished:Aug 27, 2025License:llama3Architecture:Transformer0.0K Warm

Hermes 4 70B is a 70 billion parameter hybrid-mode reasoning model developed by Nous Research, based on the Llama-3.1 architecture. It is specifically designed for advanced reasoning tasks, excelling in math, code, STEM, logic, and creative writing, while maintaining general assistant quality. The model features a unique hybrid reasoning mode with explicit deliberation segments and improved steerability for custom alignment.

Loading preview...