▲ local intelligence

can it run

Can the GTX 1050 Mobile run WHISPER tiny?

TIGHT

2.1 of 2 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

2GB · Pascal (laptop) · model file 0.1GB · tiny

~310–560 tok/s

computed roofline: 112.1 GB/s × 0.28–0.50 efficiency window / 0.1GB (Q4_K_M) — bands, never points.

Run WHISPER tiny on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs WHISPER tiny fully ($35)

→ every model the GTX 1050 Mobile can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the GTX 1050 Mobile · fit = weights + 4k KV vs usable memory