// RUN โ€” FITS

Can the FuriosaAI RNGD run Yi-1.5-9B?

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

Yi-1.5-9B on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 191k 55.2-67.1 t/s ~1.5-1.8 (slow)
Q8 yes 258k 110.4-134.2 t/s ~2.9-3.6 (slow)
Q4 yes 288k 197.2-239.6 t/s ~5.3-6.4 (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 Yi-1.5-9B?โ–ถ

Yes. At Q4 it generates ~197.2-239.6 tok/s and fits up to 288k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.3-6.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 288k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.