// RUN โ€” FITS

Can the AMD Radeon RX 6900 XT run ProteinBERT?

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

ProteinBERT on the AMD Radeon RX 6900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 201k 10080-12320 t/s ~787.5-962.5 (slow)
Q8 yes 201k 20160-24640 t/s ~1575-1925 (slow)
Q4 yes 202k 36000-44000 t/s ~2812.5-3437.5 (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 ProteinBERT?โ–ถ

Yes. At Q4 it generates ~36000-44000 tok/s and fits up to 202k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2812.5-3437.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 202k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.