// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run Hyena-2 153M?

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

Hyena-2 153M on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2668k 10911.8-13336.6 t/s ~82.4-100.7 (slow)
Q8 yes 2670k 21823.5-26673.2 t/s ~164.7-201.3 (slow)
Q4 yes 2671k 38970.6-47630.7 t/s ~294.1-359.5 (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 Hyena-2 153M?โ–ถ

Yes. At Q4 it generates ~38970.6-47630.7 tok/s and fits up to 2671k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~294.1-359.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2671k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.