Intel Outlines 40 TOPS NPU Performance As Minimum Requirement For Windows Copilot & AI PC Platforms
Intel has disclosed the compute performance that you would need to run Microsoft's Copilot locally on Windows-based AI PCs.
Running Microsoft Copilot Locally Would Require At least 40 AI TOPs, Making NPUs A Crucial Component For Intel, AMD & Future Windows-Based PCs
The possibility of running AI engines into local systems might finally come true, courtesy of Intel's dedicated Neural Processing Units integrated into next-gen CPUs. In a QnA session by Tom's Hardware at Intel's AI Summit in Taipei, it was disclosed to them that Microsoft's Copilot will finally run naively on Intel AI PCs, mentioning a 40 TOPS NPU performance requirement, which is the first time we have seen such a threshold. This marks the era of the adoption of AI PCs by consumers, and it looks like Intel's NPU tiles will further catalyze the popularity of the new PC standard.
Related Story Intel Gaudi 2 Accelerators Showcase Competitive Performance Per Dollar Against NVIDIA H100 In MLPerf 4.0 GenAI Benchmarks
Before you get your hopes up too high, it is essential to note that no current CPU in the market can match the NPU performance requirement, and the closest you can get is with AMD's Hawk Point APUs, which feature around 16 TOPS with their NPU onboard. Similarly, Intel's recently-released Meteor Lake SKUs are also way behind the requirement, which means that running Microsoft's Copilot locally would be an issue for consumers right now. However, Qualcomm's Snapdragon X Elite SoC pledges to bring 45 TOPS power through its "Hexagon" NPU, which could potentially meet Microsoft's threshold.
While with future lineups from AMD and Intel, we can anticipate the NPU performance to cross the barrier, but for now, it seems like Qualcomm is indeed in the lead, boasting almost 5 times more NPU performance than its competitors, and this is just their first entry into the CPU markets.
The era of AI PCs is indeed upon us, and with manufacturers racing against each other to integrate the technology's capability