// RUN โ€” FITS

Can the Intel Gaudi 3 run Yi-1.5-9B?

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

Yi-1.5-9B on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 752k 121.5-150.8 t/s ~1.3-1.6 (slow)
Q8 yes 820k 243-301.7 t/s ~2.6-3.3 (slow)
Q4 yes 849k 434-538.7 t/s ~4.7-5.8 (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 Yi-1.5-9B?โ–ถ

Yes. At Q4 it generates ~434-538.7 tok/s and fits up to 849k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.7-5.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 849k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.