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 AlphaGeometry?
Yes — here's how fast and up to what context, with real measured numbers.
AlphaGeometry on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 646k | 3228.5-3923.8 t/s | ~86.1-104.6 (slow) |
| Q8 | yes | 649k | 6457-7847.7 t/s | ~172.2-209.3 (slow) |
| Q4 | yes | 650k | 11530.3-14013.7 t/s | ~307.5-373.7 (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 AlphaGeometry?▶
Yes. At Q4 it generates ~11530.3-14013.7 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~307.5-373.7 tok/s.
How much context fits?▶
At Q4, up to about 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.