← Blog
Neural Engine
General/dictionary/neural-engine
Definition
Apple's on-device NPU, present in every iPhone since the A11 (2017) and every Apple Silicon Mac. Handles Face ID, on-device dictation, photo classification, and increasingly ML model inference via Core ML. 16-core in M3/M4, 38 TOPS peak.
Related terms
Posts that use this term
- Why Apple Silicon punches above its weight on local LLMs
Unified memory means the GPU sees all of RAM. Why that beats discrete-GPU PCs above 32B parameters, what fits in 16/32/64/128/192GB, and where Apple Silicon still loses.
- Where AI actually runs: cloud, local, edge
Where the model file actually sits when you use AI: a datacenter GPU (cloud), your own machine (local), or the device's silicon (edge). The trade-offs and how to pick.