# Fireworks Ai

> Markdown twin of https://roboterminal.app/companies/fireworks-ai · https://roboterminal.app/companies/fireworks-ai.md

## On shared sources

- [Baseten](https://roboterminal.app/companies/baseten) (1)
- [Fal](https://roboterminal.app/companies/fal) (1)
- [NVIDIA](https://roboterminal.app/companies/nvidia) (1)

## Pulse

- [@stretchcloud on X](https://x.com/stretchcloud/status/2112764062232670429)
  Fal and Fireworks AI just put out a number worth sitting with: 961.6 tokens per second, one request, on a 27B model, four Nvidia B300s doing the work. That's the early-launch benchmark for EAGLE-4, th…

---

Source: Roboterminal · https://roboterminal.app/companies/fireworks-ai.md