AI Agent StoreNVIDIA · Download verified
Flora TempSeg · video boundaries
Find where one action ends and another begins in a robot or human demonstration video. Use the results to prepare a robotics research dataset.
Released 2026-10-15 · First reviewed 2026-10-26 · Checked 2026-11-03.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact download ID: nvidia/Flora-TempSeg. Returns time intervals and flags for actions that continue beyond a clip; it does not name the actions. This download is an adapter: it also needs the exact Qwen3.5-9B base specified in the model card. The reference setup processes 16- or 32-second windows.
For non-commercial robotics research and development only, under the NVIDIA OneWay Noncommercial License. These tools label videos; they are not supported for production use, direct robot control or use as the sole safety monitor.
Follow the publisher’s frame-sampling and timing instructions. Its reference setup uses a 32,768-token sequence budget; this is not a verified general-purpose context limit.
Downloadable research model; no hosted token price is established.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗