🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the FuriosaAI RNGD run Retrieval-Augmented Generator?
Yes — here's how fast and up to what context, with real measured numbers.
Retrieval-Augmented Generator on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 632k | 778.8-946.5 t/s | ~20.8-25.2 (slow) |
| Q8 | yes | 641k | 1557.5-1893 t/s | ~41.5-50.5 (slow) |
| Q4 | yes | 646k | 2781.3-3380.3 t/s | ~74.2-90.1 (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 Retrieval-Augmented Generator?▶
Yes. At Q4 it generates ~2781.3-3380.3 tok/s and fits up to 646k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~74.2-90.1 tok/s.
How much context fits?▶
At Q4, up to about 646k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.