Developer Open-Sources Real-Time VLM Scene Understanding on AGX Thor

A developer open-sourced a real-time VLM scene understanding system on Jetson AGX Thor with RealSense depth cameras, achieving 4Hz spatial descriptions and 75ms per-frame depth inference with a local Qwen model.

2026-09-04 ~ 2026-09-04 · 3 related posts

• RealSense SDK v2.58.4 update lets local Qwen model describe robot spatial awareness at 4Hz — chrismatthieu · 2026-09-04
• NVIDIA AGX Thor + RealSense hits 75ms per VLM depth inference, ~10-12 FPS scenes — chrismatthieu · 2026-09-04
• Real-time VLM on Jetson AGX Thor: 10-12 scene inferences per second at ~75ms, open source — chrismatthieu · 2026-09-04