// RUN โ€” FITS

Can the AMD Instinct MI455X run ESM1-670M (UR50/D)?

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

ESM1-670M (UR50/D) on the AMD Instinct MI455X

QuantFits?Max contextSpeedBeyond context
FP16 yes 6021k 9225.9-11276.2 t/s ~18.8-23 (slow)
Q8 yes 6031k 18451.9-22552.3 t/s ~37.7-46 (slow)
Q4 yes 6036k 32949.8-40272 t/s ~67.2-82.2 (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 MI455X run ESM1-670M (UR50/D)?โ–ถ

Yes. At Q4 it generates ~32949.8-40272 tok/s and fits up to 6036k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~67.2-82.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 6036k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.