Single RTX 5090 Serves 256 Concurrent Requests at ~18K Tokens/s

Chutes, part of the Bittensor ecosystem, unveiled Parallax, which handled 256 concurrent requests on a single consumer RTX 5090 at nearly 18,000 tokens/s, at a cost of about one cent per million tokens.

2026-11-13 ~ 2026-11-13 · 2 related posts

• Chutes' Parallax hits ~18,000 tok/s on one RTX 5090, ~1 cent per million tokens — bittingthembits · 2026-11-13
• Bittensor's Chutes Handles 256 Concurrent Requests on a Single RTX 5090 at ~18k tok/s — markjeffrey · 2026-11-13