▲ local intelligence

can it run

Can the AMD Radeon Instinct MI60 run WHISPER small?

FULL

2.9 GB needed of 32 GB usable — headroom for context

32GB · GCN5.1 · model file 0.9GB · small

~320–510 tok/s

computed roofline: 1024 GB/s × 0.28–0.45 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 3090 (24GB, used) — upgrade path machine

→ every model the AMD Radeon Instinct MI60 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the AMD Radeon Instinct MI60 · fit = weights + 4k KV vs usable memory