local intelligence

can it run

Can the Radeon PRO W7800 32GB run llava 7B?

FULL

6.7 GB needed of 32 GB usable — headroom for context

32GB · RDNA3 · model file 4.7GB · 7B

~61–92 tok/s

computed roofline: 576 GB/s × 0.50–0.75 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run llava 7B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs llava 7B fully ($35)

Radeon AI PRO R9700 (32GB) — upgrade path machine

every model the Radeon PRO W7800 32GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the Radeon PRO W7800 32GB · fit = weights + 4k KV vs usable memory