Linux developers can now leverage Intel’s Neural Processing Unit via openSUSE, enabling faster, more efficient, and more accessible AI development on everyday hardware.
The openSUSE project has begun distributing packaging for the Intel Neural Processing Unit (NPU) driver, enabling small-scale AI development on Linux. Support is available through openSUSE’s Tumbleweed rolling-release distribution, giving developers direct access to Intel’s built-in CPU accelerator for AI workloads on laptops and PCs.
NPUs offer better performance and lower power consumption than traditional CPUs and GPUs on smaller hardware, making AI more practical for everyday devices. To utilise the NPU fully, developers require OpenVINO user-space software, developed by Intel and optimised for low power, low latency, and edge deployment. This allows AI applications to run on existing hardware without costly upgrades.
The open source kit has already supported the creation of Intel’s modular, edge-native software platform, released last year. Meanwhile, the OpenVINO Model Server is designed for cloud and server deployments and remains compatible with hyperscaler cloud storage.
“With the arrival of NPU (Neural Processing Unit) devices, it has become possible to run LLMs and generative AI applications without relying on a dedicated GPU … As members of an open source community, we have a responsibility to democratize emerging technologies and help reduce the digital divide, and this delivery is another important step in that direction,” Alessandro de Oliveira Faria, Innovator, Intel.
By integrating OpenVINO and NPUs into an open source environment, openSUSE empowers Linux developers to experiment with AI on everyday hardware, democratising access to advanced AI technology and fostering community-driven edge-based AI development.
