▲ local intelligence

can it run

Can the NVIDIA RTX 2070 run WHISPER tiny?

FULL

2.1 GB needed of 8 GB usable — headroom for context

8GB · Turing TU106 · model file 0.1GB · tiny

~2200–3200 tok/s

computed roofline: 448 GB/s × 0.48–0.72 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 3090 (24GB, used) — upgrade path machine

→ every model the NVIDIA RTX 2070 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 2070 · fit = weights + 4k KV vs usable memory