▲ local intelligence

can it run

Can the Radeon Vega 3 (iGPU) run WHISPER base?

FULL

2.3 GB needed of 5.5 GB usable — headroom for context

~5.5GB usable · GCN5.1 (iGPU) · model file 0.3GB · base

~32–100 tok/s

computed roofline: 38.4 GB/s × 0.25–0.80 efficiency window / 0.3GB (Q4_K_M) — bands, never points.

Run WHISPER base on instead

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

→ every model the Radeon Vega 3 (iGPU) can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the Radeon Vega 3 (iGPU) · fit = weights + 4k KV vs usable memory