OpceanAI/Yuuki-NxG
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Feb 23, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

OpceanAI/Yuuki-NxG is a 3-billion parameter language model built on the Qwen2.5 architecture, fine-tuned for open-ended conversation, emotional support, and general-purpose reasoning. Uniquely, it was trained entirely on a Mac Pro (2020) with zero cloud compute budget, demonstrating accessible alignment fine-tuning. It achieves the highest TruthfulQA score among compared 3B-scale models, indicating improved factual honesty, and is optimized for companion-purpose applications.

Loading preview...