About this AI Chat

The AI Inference Extension enables LLM models to run on Chromia network nodes instead of centralized cloud services like AWS. Inputs and outputs are managed via blockchain transactions, processed and validated by multiple nodes. Currently available on Testnet, it supports CPU- and GPU-based models. This demo uses Qwen2.5-1.5B-Instruct, running on GPU-enabled nodes.

Please note that the model used in this demo does not have access to up to date information. Its responses are based solely on its trained data and the context provided during each conversation.