// RUN โ€” FITS

Can the NVIDIA A100 PCIe 80GB run FunSearch?

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

FunSearch on the NVIDIA A100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 161k 47.1-56.1 t/s ~1-1.2 (slow)
Q8 yes 218k 94.2-112.2 t/s ~1.9-2.3 (slow)
Q4 yes 243k 168.2-200.4 t/s ~3.5-4.1 (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 NVIDIA A100 PCIe 80GB run FunSearch?โ–ถ

Yes. At Q4 it generates ~168.2-200.4 tok/s and fits up to 243k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.5-4.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 243k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.