// RUN โ€” FITS

Can the Intel Gaudi 3 run Emu2?

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

Emu2 on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 161k 29-36 t/s ~0.3-0.4 (slow)
Q8 yes 302k 58-72 t/s ~0.6-0.8 (slow)
Q4 yes 364k 103.6-128.6 t/s ~1.1-1.4 (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 Emu2?โ–ถ

Yes. At Q4 it generates ~103.6-128.6 tok/s and fits up to 364k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.1-1.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 364k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.