// RUN โ€” FITS

Can the FuriosaAI RNGD run ESM1v?

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

ESM1v on the FuriosaAI RNGD

QuantFits?Max contextSpeedBeyond context
FP16 yes 631k 750-911.5 t/s ~20-24.3 (slow)
Q8 yes 641k 1500-1823.1 t/s ~40-48.6 (slow)
Q4 yes 645k 2678.6-3255.5 t/s ~71.4-86.8 (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 ESM1v?โ–ถ

Yes. At Q4 it generates ~2678.6-3255.5 tok/s and fits up to 645k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~71.4-86.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 645k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.