// RUN โ€” FITS

Can the Instinct MI430X run MAI-DS-R1?

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

MAI-DS-R1 on the Instinct MI430X

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 no โ€” โ€” โ€”
Q4 yes 38k 39.1-47.7 t/s ~0.1-0.1 (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 MI430X run MAI-DS-R1?โ–ถ

Yes. At Q4 it generates ~39.1-47.7 tok/s and fits up to 38k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.1-0.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 38k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.