// RUN โ€” FITS

Can the AMD Radeon RX 7900 XTX run Domyn Small?

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

Domyn Small on the AMD Radeon RX 7900 XTX

QuantFits?Max contextSpeedBeyond context
FP16 yes 4k 30.2-37 t/s ~1.3-1.5 (slow)
Q8 yes 65k 60.5-73.9 t/s ~2.5-3.1 (slow)
Q4 yes 91k 108-132 t/s ~4.5-5.5 (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 7900 XTX run Domyn Small?โ–ถ

Yes. At Q4 it generates ~108-132 tok/s and fits up to 91k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.5-5.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 91k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.