// RUN โ€” FITS

Can the Intel Gaudi 3 run LUKE?

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

LUKE on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1759k 2221.5-2757.8 t/s ~24-29.8 (slow)
Q8 yes 1767k 4443.1-5515.5 t/s ~48-59.6 (slow)
Q4 yes 1770k 7934-9849.2 t/s ~85.8-106.5 (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 LUKE?โ–ถ

Yes. At Q4 it generates ~7934-9849.2 tok/s and fits up to 1770k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~85.8-106.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1770k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.