// RUN โ€” FITS

Can the AMD Ryzen AI Max+ 395 run UniRep?

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

UniRep on the AMD Ryzen AI Max+ 395

QuantFits?Max contextSpeedBeyond context
FP16 yes 1734k 4430.8-5415.4 t/s ~173.1-211.5 (slow)
Q8 yes 1735k 8861.5-10830.8 t/s ~346.2-423.1 (slow)
Q4 yes 1735k 15824.2-19340.7 t/s ~618.1-755.5 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the AMD Ryzen AI Max+ 395 run UniRep?โ–ถ

Yes. At Q4 it generates ~15824.2-19340.7 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~618.1-755.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.