// RUN โ€” FITS

Can the Intel Gaudi 3 run gte-modernbert?

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

gte-modernbert on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1769k 7201.3-8939.6 t/s ~77.9-96.6 (slow)
Q8 yes 1772k 14402.7-17879.2 t/s ~155.7-193.3 (slow)
Q4 yes 1773k 25719.1-31927.1 t/s ~278-345.2 (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 gte-modernbert?โ–ถ

Yes. At Q4 it generates ~25719.1-31927.1 tok/s and fits up to 1773k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~278-345.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1773k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.