local intelligence

can it run

Can the AMD Radeon RX 7900 XTX run WHISPER small?

FULL

2.9 GB needed of 24 GB usable — headroom for context

24GB · RDNA3 · model file 0.9GB · small

~530–800 tok/s

computed roofline: 960 GB/s × 0.50–0.75 efficiency window / 0.9GB (Q4_K_M) — bands, never points.

Run WHISPER small on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs WHISPER small fully ($110)

rtx-3090 — the next step up from AMD Radeon RX 7900 XTX

every model the AMD Radeon RX 7900 XTX can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the AMD Radeon RX 7900 XTX · fit = weights + 4k KV vs usable memory