// RUN โ€” FITS

Can the Intel Gaudi 3 run HiDream-I1?

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

HiDream-I1 on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 306k 59.6-74 t/s ~0.6-0.8 (slow)
Q8 yes 375k 119.2-148 t/s ~1.3-1.6 (slow)
Q4 yes 405k 212.9-264.3 t/s ~2.3-2.9 (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 HiDream-I1?โ–ถ

Yes. At Q4 it generates ~212.9-264.3 tok/s and fits up to 405k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.3-2.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 405k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.