Roboflow
Open-source inference package and server that turns a computer or edge device into a vision deployment target.
Roboflow Inference is a Python package and matching HTTP server that handles model loading, pre- and post-processing, CPU and GPU optimisation and workflow execution. The core library is Apache 2.0 licensed, with separate licences for some model and enterprise directories.
Workstation, edge device or on-premise server
Specifications taken from current manufacturer documentation and last checked on 2026-09-08.
Source: manufacturer documentation
Specifications are summarised from publicly published manufacturer material and are provided for orientation only. Always confirm current figures directly with the manufacturer before purchasing or designing in.
Open-source vision model family covering detection, segmentation, classification, pose and oriented boxes.
GPU-accelerated SDK for building real-time video analytics pipelines on Jetson and x86 GPUs.