// RUN โ€” FITS

Can the Intel Gaudi 3 run StyleGAN2?

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

StyleGAN2 on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1773k 35766.7-44400 t/s ~386.7-480 (slow)
Q8 yes 1774k 71533.3-88800 t/s ~773.3-960 (slow)
Q4 yes 1774k 127738.1-158571.4 t/s ~1381-1714.3 (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 Intel Gaudi 3 run StyleGAN2?โ–ถ

Yes. At Q4 it generates ~127738.1-158571.4 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1381-1714.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1774k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.