// RUN โ€” FITS

Can the FuriosaAI RNGD run Genie 2 (bio)?

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

Genie 2 (bio) on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 650k 31051-37738.9 t/s ~828-1006.4 (slow)
Q8 yes 651k 62101.9-75477.7 t/s ~1656.1-2012.7 (slow)
Q4 yes 651k 110896.3-134781.6 t/s ~2957.2-3594.2 (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 FuriosaAI RNGD run Genie 2 (bio)?โ–ถ

Yes. At Q4 it generates ~110896.3-134781.6 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2957.2-3594.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 651k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.