// RUN โ€” FITS

Can the Intel Gaudi 3 run BLOOM-7.1B?

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

BLOOM-7.1B on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 779k 151.8-188.4 t/s ~1.6-2 (slow)
Q8 yes 833k 303.5-376.8 t/s ~3.3-4.1 (slow)
Q4 yes 857k 542-672.9 t/s ~5.9-7.3 (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 BLOOM-7.1B?โ–ถ

Yes. At Q4 it generates ~542-672.9 tok/s and fits up to 857k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.9-7.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 857k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.