local intelligence

can it run

Can the Apple M4 Max run moondream 2B?

FULL

3.7 GB needed of 34 GB usable — headroom for context

~34GB usable · Apple M4 Max · model file 1.7GB · 2B

~180–260 tok/s

computed roofline: 546 GB/s × 0.55–0.80 efficiency window / 1.7GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).

Run moondream 2B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs moondream 2B fully ($110)

every model the Apple M4 Max 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 M4 Max · fit = weights + 4k KV vs usable memory