local intelligence

can it run

Can the Apple M2 Pro run WHISPER tiny?

FULL

2.1 GB needed of 14 GB usable — headroom for context

~14GB usable · Apple M2 Pro · model file 0.1GB · tiny

~1100–1600 tok/s

computed roofline: 200 GB/s × 0.55–0.80 efficiency window / 0.1GB (Q4_K_M) — bands, never points.

Run WHISPER tiny on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs WHISPER tiny fully ($110)

every model the Apple M2 Pro can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Apple M2 Pro · fit = weights + 4k KV vs usable memory