local intelligence

can it run

Can the AMD Radeon RX 7900 GRE run llava 13B?

FULL

11.1 GB needed of 16 GB usable — headroom for context

16GB · RDNA3 · model file 8.0GB · 13B

~36–54 tok/s

computed roofline: 576 GB/s × 0.50–0.75 efficiency window / 8.0GB (Q4_K_M) — bands, never points.

Run llava 13B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs llava 13B fully ($135)

rx-7900-xtx — the next step up from AMD Radeon RX 7900 GRE

every model the AMD Radeon RX 7900 GRE 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 GRE · fit = weights + 4k KV vs usable memory