// RUN โ€” FITS

Can the NVIDIA A100 PCIe 80GB run Falcon-40B?

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

Falcon-40B on the NVIDIA A100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 98k 35.3-42.1 t/s ~0.7-0.9 (slow)
Q4 yes 152k 63.1-75.2 t/s ~1.3-1.6 (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 Falcon-40B?โ–ถ

Yes. At Q4 it generates ~63.1-75.2 tok/s and fits up to 152k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.3-1.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 152k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.