local intelligence

can it run

Can the NVIDIA H100 NVL 94GB run WHISPER medium?

FULL

5.1 GB needed of 94 GB usable — headroom for context

94GB · Hopper · model file 3.1GB · medium

~580–960 tok/s

computed roofline: 3900 GB/s × 0.46–0.76 efficiency window / 3.1GB (Q4_K_M) — bands, never points.

Run WHISPER medium on instead

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

H100 80GB PCIe (used) — upgrade path machine

every model the NVIDIA H100 NVL 94GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the NVIDIA H100 NVL 94GB · fit = weights + 4k KV vs usable memory