local intelligence

can it run

Can the GeForce MX350 run qwen3 1.7B?

TIGHT

1.8 of 2 GB usable — keep context modest

2GB · Pascal (laptop) · model file 1.4GB · 1.7B

~11–20 tok/s

computed roofline: 56 GB/s × 0.28–0.50 efficiency window / 1.4GB (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 qwen3 1.7B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs qwen3 1.7B 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