// RUN โ€” FITS

Can the AMD Radeon RX 9070 XT run DistilProtBert?

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

DistilProtBert on the AMD Radeon RX 9070 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 195k 882-1078 t/s ~54.8-67 (slow)
Q8 yes 198k 1764-2156 t/s ~109.6-133.9 (slow)
Q4 yes 200k 3150-3850 t/s ~195.7-239.1 (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 9070 XT run DistilProtBert?โ–ถ

Yes. At Q4 it generates ~3150-3850 tok/s and fits up to 200k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~195.7-239.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.