Uploaded July 2024 | Updated November 2026, 1 hour ago
In this video we'll "bootstrap" (create out of nothing) a fully-functioning AI application with Gradio and Hugging Face's ZeroGPU spaces.
The application will be free to build and take less than 5 minutes and 100 lines of code!
We will build a Compliment Bot - users upload a photo of themselves or their friends and the bot will say something nice about them! The AI models used in this space will be running on Hugging Face's innovative ZeroGPU cluster - a serverless cluster of A100s that is FREE to use. We'll leverage these spaces in our application using the Gradio javascript client. That way, we can bring AI into our applications instantly without having to host or train anything ourselves.
Resources:
1 - Final App and Code: huggingface.co/spaces/freddyaboulton/compliment-bot-static
2 - SD3 Long Captioner Space: huggingface.co/spaces/gokaygokay/SD3-Long-Captioner
3 - huggingface.co/spaces/hysts/zephyr-7b
4- Blog post going into more depth: details:freddyboulton.com/blog/building-with-zero-gpu
In this video we'll "bootstrap" (create out of nothing) a fully-functioning AI application with Gradio and Hugging Face's ZeroGPU spaces.
The application will be free to build and take less than 5 minutes and 100 lines of code!
We will build a Compliment Bot - users upload a photo of themselves or their friends and the bot will say something nice about them! The AI models used in this space will be running on Hugging Face's innovative ZeroGPU cluster - a serverless cluster of A100s that is FREE to use. We'll leverage these spaces in our application using the Gradio javascript client. That way, we can bring AI into our applications instantly without having to host or train anything ourselves.
Resources:
1 - Final App and Code: huggingface.co/spaces/freddyaboulton/compliment-bot-static
2 - SD3 Long Captioner Space: huggingface.co/spaces/gokaygokay/SD3-Long-Captioner
3 - huggingface.co/spaces/hysts/zephyr-7b
4- Blog post going into more depth: details:freddyboulton.com/blog/building-with-zero-gpu


- RTX 5090 llama.cpp runs of Qwen3.8-27B Q4_K_M: [https://huggingface.co/Qwen/Qwen3.8-27B/discussions/112](https://huggingface.co/Qwen/Qwen3.8-27B/discussions/112)
- MacStories M5 Ultra review (same prompts on both machines): [https://www.macstories.net/stories/m5-ultra-mac-studio-review-the-dream-mac-for-local-ai-agents/](https://www.macstories.net/stories/m5-ultra-mac-studio-review-the-dream-mac-for-local-ai-agents/)
Chapters:
0:00 Intro
0:19 The spec sheet
1:20 Same model, head to head
2:25 Memory: 32 GB vs 256 GB
2:41 What to take away RTX 5090 vs M5 Ultra: Which AI Powerhouse Wins?](https://i.ytimg.com/vi/qaP4pymNrEc/mqdefault.jpg)








