// RUN โ€” FITS

Can the AMD Radeon RX 7900 XTX run MegaMolBART?

Yes โ€” here's how fast and up to what context, with real measured numbers.

MegaMolBART on the AMD Radeon RX 7900 XTX

QuantFits?Max contextSpeedBeyond context
FP16 yes 313k 6720-8213.3 t/s ~280-342.2 (slow)
Q8 yes 313k 13440-16426.7 t/s ~560-684.4 (slow)
Q4 yes 314k 24000-29333.3 t/s ~1000-1222.2 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the AMD Radeon RX 7900 XTX run MegaMolBART?โ–ถ

Yes. At Q4 it generates ~24000-29333.3 tok/s and fits up to 314k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1000-1222.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 314k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.