// RUN โ€” FITS

Can the Instinct MI440X run ESM1-85M?

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

ESM1-85M on the Instinct MI440X

QuantFits?Max contextSpeedBeyond context
FP16 yes 6039k 72549.9-88672.2 t/s ~148.1-181 (slow)
Q8 yes 6040k 145099.9-177344.3 t/s ~296.1-361.9 (slow)
Q4 yes 6041k 259106.9-316686.3 t/s ~528.8-646.3 (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 Instinct MI440X run ESM1-85M?โ–ถ

Yes. At Q4 it generates ~259106.9-316686.3 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~528.8-646.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 6041k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.