// RUN โ€” FITS

Can the Instinct MI455X run BIDAF?

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

BIDAF on the Instinct MI455X

QuantFits?Max contextSpeedBeyond context
FP16 yes 6041k 2374615.4-2902307.7 t/s ~4846.2-5923.1 (slow)
Q8 yes 6042k 4749230.8-5804615.4 t/s ~9692.3-11846.2 (slow)
Q4 yes 6042k 8480769.2-10365384.6 t/s ~17307.7-21153.8 (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 MI455X run BIDAF?โ–ถ

Yes. At Q4 it generates ~8480769.2-10365384.6 tok/s and fits up to 6042k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17307.7-21153.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 6042k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.