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 FvFold?
Yes — here's how fast and up to what context, with real measured numbers.
FvFold on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 651k | 52932.8-64333.7 t/s | ~1411.5-1715.6 (slow) |
| Q8 | yes | 651k | 105865.6-128667.5 t/s | ~2823.1-3431.1 (slow) |
| Q4 | yes | 651k | 189045.8-229763.3 t/s | ~5041.2-6127 (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 FvFold?▶
Yes. At Q4 it generates ~189045.8-229763.3 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5041.2-6127 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.