New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA H200 run DiffDock?
Yes — here's how fast and up to what context, with real measured numbers.
DiffDock on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1956k | 86561.3-103162.1 t/s | ~721.3-859.7 (slow) |
| Q8 | yes | 1956k | 173122.5-206324.1 t/s | ~1442.7-1719.4 (slow) |
| Q4 | yes | 1956k | 309147.4-368435.9 t/s | ~2576.2-3070.3 (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 H200 run DiffDock?▶
Yes. At Q4 it generates ~309147.4-368435.9 tok/s and fits up to 1956k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2576.2-3070.3 tok/s.
How much context fits?▶
At Q4, up to about 1956k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.