RunSnack – P2P GPU sharing with a link. Would love feedback from ML people who rent/rent out GPUs

Site Feedback
1

Hey HF community,

I built a tool that might be relevant to a lot of people here who either have idle GPUs or need compute for quick jobs. It’s called RunSnack — share your GPU with a single link. No accounts, no cloud, no platform fees.

Why this matters for ML people:

  • Need an A100 for 2 hours of inference testing? Find a host, get a link, instant terminal.

  • Got a 4090 sitting idle overnight? Share it, set your price, negotiate directly.

  • No KYC, no cloud markup, no usage logs. Just P2P compute.

How it works:

  1. Host runs a script → gets a shareable link

  2. Renter opens link in browser → instant xterm.js terminal with GPU access

  3. Everything runs inside a sandboxed Docker container (read-only, privilege-dropped)

  4. WebRTC data channel — encrypted, P2P, no central server sees your data

  5. Marketplace is organic: post on Discord what you need or offer, negotiate, share link

Built for the “quick GPU snack” use case:

  • ML researcher needs 30 min of inference on a GPU they don’t own

  • Student wants to fine-tune a model for a few hours without spinning up a cloud instance

  • Someone with a homelab GPU wants to monetize idle time

I’d love feedback from this community on:

  1. Would you use this? Why or why not?

  2. Security concerns? Docker sandbox + GPU passthrough — what would make you trust it enough to either host or rent?

  3. What’s missing? Pre-installed ML frameworks? Persistent storage? Something else?

  4. Pricing expectations? What would you pay per hour for, say, a 4090 vs an Jetson Nano via a P2P link like this?

  5. Is this approach a competitor for sites like RunPod?

Thank you!

4

Lastly, I add this 30-sec YouTube reel so everyone gets better the idea

5

NEW — now compatible with DGX Spark (in addition to NVIDIA Jetson (JetPack 6.1) and AMD64) :blush: We keep growing.