▲ local intelligence

can it run

Can the GTX 970M run WHISPER base?

FULL

2.3 GB needed of 3 GB usable — headroom for context

3GB · Maxwell (laptop) · model file 0.3GB · base

~110–200 tok/s

computed roofline: 120.3 GB/s × 0.28–0.50 efficiency window / 0.3GB (Q4_K_M) — bands, never points.

Run WHISPER base on instead

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

→ every model the GTX 970M 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 970M · fit = weights + 4k KV vs usable memory