local intelligence

can it run

Can the GeForce MX350 run kokoro 82M?

OFFLOAD PARTIAL

2.3 GB vs 2 GB usable — partial CPU offload, expect large speed loss

2GB · Pascal (laptop) · model file 0.3GB · 82M

~52–93 tok/s

computed roofline: 56 GB/s × 0.28–0.50 efficiency window / 0.3GB (Q4_K_M) — bands, never points.

Run kokoro 82M on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs kokoro 82M fully ($110)

every model the GeForce MX350 can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the GeForce MX350 · fit = weights + 4k KV vs usable memory