▲ local intelligence

can it run

Can the GTX 980M run WHISPER small?

FULL

2.9 GB needed of 4 GB usable — headroom for context

4GB · Maxwell (laptop) · model file 0.9GB · small

~50–89 tok/s

computed roofline: 160.4 GB/s × 0.28–0.50 efficiency window / 0.9GB (Q4_K_M) — bands, never points.

Run WHISPER small on instead

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

→ every model the GTX 980M 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 980M · fit = weights + 4k KV vs usable memory