An NPU is a fixed-function matrix engine for small, quantized models, and its TOPS rating is a peak INT8 figure that does not predict how fast a device writes text.1 The claim that an NPU speeds up on-device text generation sits at rung 2, a lab demonstration, because three research groups that measured mobile NPUs disagree on which phase of generation it accelerates.234 An independent test of a 40 TOPS NPU measured 6.9 tokens per second on a 1.5-billion-parameter model, and its authors attribute the ceiling mainly to memory bandwidth.5
The status board places each claim on the maturity ladder; for devices, rung 5 means a product on sale whose claims an independent lab has tested. No claim below reaches it in the sources I opened.
| Name | Rung (1-5) | Best evidence | As of |
|---|---|---|---|
| Copilot+ NPU features (40+ TOPS floor) | 4 | Microsoft says the features are designed for the NPU and improve battery life;6 no independent power test found | read 2026-11-08 |
| Hailo-10H NPU, 40 TOPS rated | 3 | Independent preprint measured 6.9 tok/s at 1.87 W, against Hailo’s own 6.82 tok/s;5 one unit, one model | 2026-06-07 |
| Hexagon NPU speeding up LLM phases | 2 | Three groups report three different phase splits234 | 2026-07-06 |
| Intel Core Ultra NPU, Llama 2 7B at 18.55 tok/s | 4 | Intel’s own MLPerf Client v0.6 run, measured April 20257 | 2025-05-05 |
| Snapdragon 8 Elite Gen 6 NPU, “50% higher prefill” | 2 | Qualcomm’s figure for INT4 models, relayed by Android Authority;8 no test of a retail phone found | 2026-09-10 |
| Apple A20 Pro, “twice the AI processing” | 4 | Neural Engine doubled to 32 cores, memory bus width undisclosed;9 Apple’s claim against the A19 Pro, no independent test found, U.S. sales from 18 September10 | 2026-09-09 |
Seven sources are older than six months and flagged where they appear: Qualcomm’s TOPS guide (reprinted June 2024), Intel’s MLPerf post (May 2025), the SOSP paper (October 2025), Microsoft’s developer guide (page dated November 2025), the Edge AI and Vision summary (January 2026), UL’s Procyon notice (January 2026) and the Leiden thesis (April 2026).