// RUN โ€” FITS

Can the NVIDIA A100 PCIe 80GB run TAPE Transformer?

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

TAPE Transformer on the NVIDIA A100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1099k 18586.2-22150.7 t/s ~384.2-457.9 (slow)
Q8 yes 1100k 37172.4-44301.3 t/s ~768.4-915.8 (slow)
Q4 yes 1100k 66379.2-79109.5 t/s ~1372.2-1635.3 (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 TAPE Transformer?โ–ถ

Yes. At Q4 it generates ~66379.2-79109.5 tok/s and fits up to 1100k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1372.2-1635.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1100k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.