// RUN โ€” FITS

Can the Intel Gaudi 3 run RMBG v2.0?

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

RMBG v2.0 on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1767k 4855.2-6027.1 t/s ~52.5-65.2 (slow)
Q8 yes 1771k 9710.4-12054.3 t/s ~105-130.3 (slow)
Q4 yes 1772k 17340-21525.5 t/s ~187.5-232.7 (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 RMBG v2.0?โ–ถ

Yes. At Q4 it generates ~17340-21525.5 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~187.5-232.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1772k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.