Inference Using Local GPU Resource

Dear Agno Team,

I would like to run a model uploaded to Hugging Face using my local GPU resources.

However, I couldn’t find any relevant documentation in the official docs.

I’m wondering if I might have missed something or if this feature is planned for future updates.

Hi @coolwin20
Thanks for reaching out and for using Agno! I’ve looped in the right engineers to help with your question. We usually respond within 48 hours, but if this is urgent, just let us know, and we’ll do our best to prioritize it.
Appreciate your patience—we’ll get back to you soon! :smile:

1 Like

hey @coolwin20 here is the documentation for running huggingface with Agno HuggingFace - Agno :raising_hands:

@ayush I know about that module, but isn’t it only performing inference using the Hugging Face API? I want to perform inference using the GPU on my local computer.

hey @coolwin20 actually we dont support this feature yet , i have added this feature to community wishlist .

@ayush Thank you! I am preparing for service production in the smart farm sector using Agno. The current API-based agent framework is already excellent, but I look forward to its future on-premise support, which will make it even more useful.