// RUN โ€” FITS

Can the AMD Radeon RX 7800 XT run MSA Transformer?

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

MSA Transformer on the AMD Radeon RX 7800 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 199k 1965.6-2402.4 t/s ~126-154 (slow)
Q8 yes 200k 3931.2-4804.8 t/s ~252-308 (slow)
Q4 yes 201k 7020-8580 t/s ~450-550 (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 7800 XT run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~7020-8580 tok/s and fits up to 201k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~450-550 tok/s.

How much context fits?โ–ถ

At Q4, up to about 201k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.