can it run
8.2 of 8 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
8GB · Turing TU106 · model file 6.2GB · large-v3
computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 6.2GB (Q4_K_M) — bands, never points.
→ Tesla P100 (16GB, used) — cheapest catalog machine that runs WHISPER large-v3 fully ($135)
→ RTX 3090 (24GB, used) — upgrade path machine
→ every model the NVIDIA RTX 2070 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run