New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the FuriosaAI RNGD run DiffDock?
Yes — here's how fast and up to what context, with real measured numbers.
DiffDock on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 24086-29273.7 t/s | ~642.3-780.6 (slow) |
| Q8 | yes | 651k | 48171.9-58547.4 t/s | ~1284.6-1561.3 (slow) |
| Q4 | yes | 651k | 86021.3-104549 t/s | ~2293.9-2788 (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 FuriosaAI RNGD run DiffDock?▶
Yes. At Q4 it generates ~86021.3-104549 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2293.9-2788 tok/s.
How much context fits?▶
At Q4, up to about 651k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.