llama.cpp ignores NPUs and Apple CoreML acceleration
llama.cpp cannot use NPUs or Apple Neural Engine and CoreML acceleration, so laptop and phone hardware built for inference sits idle.
Tier II · Emerging Problems that are still building up.
4 public reports · first reported 6 June 2023 · last reported 10 April 2026
What's going wrong
Many new laptops and phones include neural processors from Apple, AMD and Microsoft-supported chips, yet llama.cpp runs models on the CPU or GPU only.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 4 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.