// RUN โ€” FITS

Can the FuriosaAI RNGD run Aya?

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

Aya on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 102k 37.5-45.6 t/s ~1-1.2 (slow)
Q8 yes 181k 75-91.2 t/s ~2-2.4 (slow)
Q4 yes 216k 133.9-162.8 t/s ~3.6-4.3 (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 Aya?โ–ถ

Yes. At Q4 it generates ~133.9-162.8 tok/s and fits up to 216k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.6-4.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 216k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.