// RUN โ€” FITS

Can the AMD Radeon RX 7900 XT run AraBERT?

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

AraBERT on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 255k 2290.9-2800 t/s ~114.5-140 (slow)
Q8 yes 256k 4581.8-5600 t/s ~229.1-280 (slow)
Q4 yes 257k 8181.8-10000 t/s ~409.1-500 (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 XT run AraBERT?โ–ถ

Yes. At Q4 it generates ~8181.8-10000 tok/s and fits up to 257k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~409.1-500 tok/s.

How much context fits?โ–ถ

At Q4, up to about 257k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.