// RUN โ€” FITS

Can the Intel Gaudi 3 run OPT-6.7B?

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

OPT-6.7B on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 785k 160.1-198.8 t/s ~1.7-2.1 (slow)
Q8 yes 836k 320.3-397.6 t/s ~3.5-4.3 (slow)
Q4 yes 858k 572-710 t/s ~6.2-7.7 (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 OPT-6.7B?โ–ถ

Yes. At Q4 it generates ~572-710 tok/s and fits up to 858k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.2-7.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 858k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.