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 HiFi - NN?
Yes — here's how fast and up to what context, with real measured numbers.
HiFi - NN on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 651k | 162500-197500 t/s | ~4333.3-5266.7 (slow) |
| Q8 | yes | 651k | 325000-395000 t/s | ~8666.7-10533.3 (slow) |
| Q4 | yes | 651k | 580357.1-705357.1 t/s | ~15476.2-18809.5 (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 HiFi - NN?▶
Yes. At Q4 it generates ~580357.1-705357.1 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~15476.2-18809.5 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.