▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 4060 Ti 8GB run WHISPER small?

FULL

2.9 GB needed of 8 GB usable — headroom for context

8GB · Ada · model file 0.9GB · small

~180–280 tok/s

computed roofline: 288 GB/s × 0.55–0.88 efficiency window / 0.9GB (Q4_K_M) — bands, never points.

Run WHISPER small on instead

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

→ rtx-4060-ti-16gb — the next step up from NVIDIA GeForce RTX 4060 Ti 8GB

→ every model the NVIDIA GeForce RTX 4060 Ti 8GB 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 GeForce RTX 4060 Ti 8GB · fit = weights + 4k KV vs usable memory