// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run MSA Transformer?

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

MSA Transformer on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2669k 16695-20405 t/s ~126-154 (slow)
Q8 yes 2671k 33390-40810 t/s ~252-308 (slow)
Q4 yes 2672k 59625-72875 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 Instinct MI300X 192GB run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~59625-72875 tok/s and fits up to 2672k 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 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.