// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run ByT5-XXL?

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

ByT5-XXL on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 911k 129.4-158.2 t/s ~1-1.2 (slow)
Q8 yes 990k 258.8-316.4 t/s ~2-2.4 (slow)
Q4 yes 1025k 462.2-564.9 t/s ~3.5-4.3 (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 MI300X 192GB run ByT5-XXL?โ–ถ

Yes. At Q4 it generates ~462.2-564.9 tok/s and fits up to 1025k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.5-4.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1025k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.