Runway open-sources robot model Praxis-1
Understand this story
Runway has open-sourced the weights and source code of its robot model Praxis-1 under the Apache 2.0 license, allowing commercial use. The model takes camera images, text instructions, and robot poses as input, predicts scene changes, and derives robotic arm actions. Developers need to register on Hugging Face and agree to the access terms before downloading. Runway's own testing shows that Praxis-1 achieves a 46.2% success rate on NVIDIA's RoboLab-120 leaderboard, higher than the 42.9% of FLUX 3 Action, which is also a World Action Model; this result has not yet been independently verified. In terms of deployment, the standard version requires a GPU with 80 GB of VRAM; according to Runway's VRAM estimates, the compressed version can fit into an RTX 5090 with 32 GB of VRAM, but the GitHub documentation states that actual peak VRAM usage has not yet been measured.
AI overview based on source reports · Updated 4 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- The DecoderRunway's open-source Praxis-1 turns video AI into a robot controller
Runway has released Praxis-1, a World Action Model that takes camera images, text instructions and robot position data to predict scene changes and derive robot movements, with weights and code under the Apache 2.0 license. Built on a video model fine-tuned with human action videos and robot data, it scored 46.2 percent on Nvidia's RoboLab-120 leaderboard, ahead of FLUX 3 Action at 42.9 percent, though Runway ran the tests itself and they have not been independently verified. The model still needs specialized robot data for adaptation, sometimes confuses similar-looking objects, and cannot reliably plan complex action sequences on its own.
Activity for this story
- Current comparable activity
- 9
- Peak comparable activity
- 10Nov 14 19:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.