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 MatterGen?
Yes — here's how fast and up to what context, with real measured numbers.
MatterGen on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 10416.7-12660.3 t/s | ~277.8-337.6 (slow) |
| Q8 | yes | 650k | 20833.3-25320.5 t/s | ~555.6-675.2 (slow) |
| Q4 | yes | 651k | 37202.4-45215.2 t/s | ~992.1-1205.7 (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 MatterGen?▶
Yes. At Q4 it generates ~37202.4-45215.2 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~992.1-1205.7 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.