// RUN โ€” FITS

Can the AMD Instinct MI325X run BLOOM-176B?

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

BLOOM-176B on the AMD Instinct MI325X

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 110k 21.4-26.2 t/s ~0.1-0.2 (slow)
Q4 yes 258k 38.3-46.8 t/s ~0.3-0.3 (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 AMD Instinct MI325X run BLOOM-176B?โ–ถ

Yes. At Q4 it generates ~38.3-46.8 tok/s and fits up to 258k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.3-0.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 258k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.