// RUN โ€” FITS

Can the FuriosaAI RNGD run Grover-Mega?

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

Grover-Mega on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 605k 325-395 t/s ~8.7-10.5 (slow)
Q8 yes 628k 650-790 t/s ~17.3-21.1 (slow)
Q4 yes 638k 1160.7-1410.7 t/s ~31-37.6 (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 FuriosaAI RNGD run Grover-Mega?โ–ถ

Yes. At Q4 it generates ~1160.7-1410.7 tok/s and fits up to 638k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~31-37.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 638k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.