// RUN โ€” FITS

Can the NVIDIA A100 SXM4 80GB run BLOOM-7.1B?

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

BLOOM-7.1B on the NVIDIA A100 SXM4 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 442k 105.3-125.5 t/s ~2.1-2.5 (slow)
Q8 yes 496k 210.5-250.9 t/s ~4.1-4.9 (slow)
Q4 yes 520k 376-448.1 t/s ~7.4-8.8 (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 NVIDIA A100 SXM4 80GB run BLOOM-7.1B?โ–ถ

Yes. At Q4 it generates ~376-448.1 tok/s and fits up to 520k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.4-8.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 520k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.