Ambarella and Ultralytics Collaborate to Bring Ultralytics YOLO Models to CVflow-Powered Edge Devices
4th article in the last 90 days, one of 15 articles referencing Ambarella. Previous coverage: Ambarella expands DevZone with cloud-hosted IDE and agentic AI development on Google Cloud Platform (Sep 2026).
Companies mentioned
Best suited for
- Seniority
- EVP / SVP / VP / AVP
- Persona
- Platform / Infrastructure Architect
- Buyer role
- Decision Maker / Budget Holder
- Buyer journey
- Need to Buy
- Adoption curve
- Early Majority
- Technology maturity
- Operational Expansion
- Industry
- Data Center / Content Delivery & Edge / CDN & Edge Delivery
Our classification, not the publisher's statement. Best suited for, not only for.
Ambarella, Inc. and Ultralytics said they completed a collaboration to support the deployment of Ultralytics YOLO models on Ambarella CVflow-powered edge devices. The update links a vision-model family to Ambarella’s edge processing platform for teams working on on-device applications.
The companies described the work as a way to connect Ultralytics’ computer vision models with Ambarella’s low-power AI processing technology. They also said the integration focused on a familiar development starting point on silicon designed around power and thermal limits used in edge products.
According to the companies, when detection, segmentation, and tracking ran locally on a device, systems could respond with lower latency, use less network bandwidth, and reduce reliance on cloud processing. The release also said Ultralytics YOLO supported object detection, instance segmentation, image classification, pose estimation, and oriented bounding box detection within a single model family, with multiple model sizes to match compute and memory budgets.
For the integration, the Ambarella side centered on the Cooper™ Developer Platform and the Ambarella Developer Zone (“DevZone”), launched at CES 2026. The release said DevZone provided optimized models, agentic blueprints, developer kits, documentation, and technical resources, and that a common CVflow architecture and shared software environment supported Ambarella’s edge AI SoC portfolio.
“By bringing Ultralytics YOLO to Ambarella’s CVflow platform, we’re making it easier for developers and product teams to build efficient, real-time vision applications directly at the edge,” said Glenn Jocher, Founder and CEO of Ultralytics. “Ultralytics YOLO is among the most widely adopted model families in computer vision, and supporting it on our CVflow platform broadens the set of teams that can build on Ambarella silicon.” said Fermi Wang, President and CEO of Ambarella.
Press release, provided by Globe Newswire on behalf of Ambarella. Read the original.