// RUN โ€” FITS

Can the FuriosaAI RNGD run ProtT5-XXL-BFD?

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

ProtT5-XXL-BFD on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 126k 44.3-53.9 t/s ~1.2-1.4 (slow)
Q8 yes 193k 88.6-107.7 t/s ~2.4-2.9 (slow)
Q4 yes 223k 158.3-192.4 t/s ~4.2-5.1 (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 ProtT5-XXL-BFD?โ–ถ

Yes. At Q4 it generates ~158.3-192.4 tok/s and fits up to 223k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.2-5.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 223k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.