// RUN — FITS

Can the NVIDIA H200 run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?

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

(ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) on the NVIDIA H200

QuantFits?Max contextSpeedBeyond context
FP16 yes 1951k 9470.3-11286.5 t/s ~78.9-94.1 (slow)
Q8 yes 1954k 18940.5-22573 t/s ~157.8-188.1 (slow)
Q4 yes 1955k 33822.4-40308.9 t/s ~281.9-335.9 (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 H200 run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?

Yes. At Q4 it generates ~33822.4-40308.9 tok/s and fits up to 1955k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~281.9-335.9 tok/s.

How much context fits?

At Q4, up to about 1955k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.