▲ local intelligence

can it run

Can the NVIDIA RTX 3090 run WHISPER tiny?

FULL

2.1 GB needed of 24 GB usable — headroom for context

24GB · Ampere GA102 · model file 0.1GB · tiny

~4300–7100 tok/s

computed roofline: 936 GB/s × 0.46–0.76 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)

→ rtx-5090 — the next step up from NVIDIA RTX 3090

→ every model the NVIDIA RTX 3090 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA RTX 3090 · fit = weights + 4k KV vs usable memory