// RUN โ€” FITS

Can the NVIDIA A100 PCIe 80GB run Flan UL2?

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

Flan UL2 on the NVIDIA A100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 126k 36.2-43.2 t/s ~0.7-0.9 (slow)
Q8 yes 201k 72.4-86.3 t/s ~1.5-1.8 (slow)
Q4 yes 233k 129.4-154.2 t/s ~2.7-3.2 (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 NVIDIA A100 PCIe 80GB run Flan UL2?โ–ถ

Yes. At Q4 it generates ~129.4-154.2 tok/s and fits up to 233k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.7-3.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 233k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.