// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run MSA Transformer?

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

MSA Transformer on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 648k 2721.6-3326.4 t/s ~126-154 (slow)
Q8 yes 649k 5443.2-6652.8 t/s ~252-308 (slow)
Q4 yes 650k 9720-11880 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 Pro W7900 48GB run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~9720-11880 tok/s and fits up to 650k 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 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.