local intelligence

can it run

Can the RTX 4070 Laptop run WHISPER large-v3?

TIGHT

8.2 of 8 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

8GB · Ada AD106 · model file 6.2GB · large-v3

~33–55 tok/s

computed roofline: 448 GB/s × 0.46–0.76 efficiency window / 6.2GB (Q4_K_M) — bands, never points.

Run WHISPER large-v3 on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs WHISPER large-v3 fully ($135)

every model the RTX 4070 Laptop can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the RTX 4070 Laptop · fit = weights + 4k KV vs usable memory