▲ local intelligence

can it run

Can the GeForce MX150 run qwen3 8B?

NO

5.8 GB vs 2 GB usable — does not fit

2GB · Pascal (laptop) · model file 5.2GB · 8B

~2.6–4.6 tok/s

computed roofline: 48 GB/s × 0.28–0.50 efficiency window / 5.2GB (Q4_K_M) — bands, never points.

Run qwen3 8B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs qwen3 8B fully ($35)

→ every model the GeForce MX150 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the GeForce MX150 · fit = weights + 4k KV vs usable memory