// RUN โ€” FITS

Can the Instinct MI440X run s1.1?

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

s1.1 on the Instinct MI440X

QuantFits?Max contextSpeedBeyond context
FP16 yes 1266k 192.9-235.8 t/s ~0.4-0.5 (slow)
Q8 yes 1388k 385.9-471.6 t/s ~0.8-1 (slow)
Q4 yes 1442k 689.1-842.2 t/s ~1.4-1.7 (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 s1.1?โ–ถ

Yes. At Q4 it generates ~689.1-842.2 tok/s and fits up to 1442k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.4-1.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1442k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.