// RUN โ€” FITS

Can the Intel Gaudi 3 run SimpleFold?

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

SimpleFold on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1682k 357.7-444 t/s ~3.9-4.8 (slow)
Q8 yes 1728k 715.3-888 t/s ~7.7-9.6 (slow)
Q4 yes 1748k 1277.4-1585.7 t/s ~13.8-17.1 (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 SimpleFold?โ–ถ

Yes. At Q4 it generates ~1277.4-1585.7 tok/s and fits up to 1748k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13.8-17.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1748k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.