// RUN โ€” FITS

Can the Intel Gaudi 3 run GemNet-T (OC20)?

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

GemNet-T (OC20) on the Intel Gaudi 3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1774k 564736.8-701052.6 t/s ~6105.3-7578.9 (slow)
Q8 yes 1774k 1129473.7-1402105.3 t/s ~12210.5-15157.9 (slow)
Q4 yes 1774k 2016917.3-2503759.4 t/s ~21804.5-27067.7 (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 GemNet-T (OC20)?โ–ถ

Yes. At Q4 it generates ~2016917.3-2503759.4 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~21804.5-27067.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1774k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.