// RUN โ€” FITS

Can the AMD Radeon RX 6900 XT run OntoProtein?

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

OntoProtein on the AMD Radeon RX 6900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 189k 384-469.3 t/s ~30-36.7 (slow)
Q8 yes 195k 768-938.7 t/s ~60-73.3 (slow)
Q4 yes 198k 1371.4-1676.2 t/s ~107.1-131 (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 6900 XT run OntoProtein?โ–ถ

Yes. At Q4 it generates ~1371.4-1676.2 tok/s and fits up to 198k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~107.1-131 tok/s.

How much context fits?โ–ถ

At Q4, up to about 198k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.