GPT in one dependency-free C file pushes 10M tok/sec on Apple M5
A single-file, pure-C character transformer trains on 32k names in seconds and samples at 10.1M tok/sec on Apple M5 Pro via NEON (6.9M on AVX2 x86). The 4,192-parameter model beats an interpolated trigram on held-out data, and docs break down the specialized single-token inference path.