// RUN โ€” FITS

Can the AMD Instinct MI455X run FRED-T5-XL?

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

FRED-T5-XL on the AMD Instinct MI455X

QuantFits?Max contextSpeedBeyond context
FP16 yes 5988k 3548.3-4336.8 t/s ~7.2-8.9 (slow)
Q8 yes 6015k 7096.6-8673.6 t/s ~14.5-17.7 (slow)
Q4 yes 6027k 12672.4-15488.5 t/s ~25.9-31.6 (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 MI455X run FRED-T5-XL?โ–ถ

Yes. At Q4 it generates ~12672.4-15488.5 tok/s and fits up to 6027k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~25.9-31.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 6027k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.