# Runpod

> Markdown twin of https://roboterminal.app/companies/runpod · https://roboterminal.app/companies/runpod.md

## On shared sources

- [Bittensor](https://roboterminal.app/companies/bittensor) (1)
- [Lium](https://roboterminal.app/companies/lium) (1)
- [Prime Intellect](https://roboterminal.app/companies/prime-intellect) (1)
- [Qwen](https://roboterminal.app/companies/qwen) (1)

## Pulse

- [@stretchcloud on X](https://x.com/stretchcloud/status/2096679828825190746)
  The inference cost gap between centralized APIs and decentralized GPU networks is getting hard to ignore. Qwen3.6 35B running at 14,499 tokens per second on a single B200 GPU on Lium. 85% cheaper than…

---

Source: Roboterminal · https://roboterminal.app/companies/runpod.md