// RUN โ€” FITS

Can the AMD Instinct MI455X run Refact-1.6B?

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

Refact-1.6B on the AMD Instinct MI455X

QuantFits?Max contextSpeedBeyond context
FP16 yes 5993k 3858.8-4716.3 t/s ~7.9-9.6 (slow)
Q8 yes 6017k 7717.5-9432.5 t/s ~15.8-19.3 (slow)
Q4 yes 6028k 13781.3-16843.8 t/s ~28.1-34.4 (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 Refact-1.6B?โ–ถ

Yes. At Q4 it generates ~13781.3-16843.8 tok/s and fits up to 6028k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~28.1-34.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 6028k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.