XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Feb 7, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Helcyon-Mercury-12B-v3.2 by HardWire and XeyonAI is a 12 billion parameter conversational AI model, based on Mistral Nemo 12B, with a 32768 token context length. It is specifically fine-tuned for "conversational presence," excelling in natural dialogue, emotional intelligence, consistent identity, and deep roleplay. This model is designed for users seeking nuanced, long-form interactions and creative writing support, offering enhanced tone control and expanded emotional range.

Loading preview...