// RUN โ€” FITS

Can the FuriosaAI RNGD run ESM2-150M?

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

ESM2-150M on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 646k 3250-3950 t/s ~86.7-105.3 (slow)
Q8 yes 649k 6500-7900 t/s ~173.3-210.7 (slow)
Q4 yes 650k 11607.1-14107.1 t/s ~309.5-376.2 (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 ESM2-150M?โ–ถ

Yes. At Q4 it generates ~11607.1-14107.1 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~309.5-376.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.