🔌
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 FoundationStereo?
Yes — here's how fast and up to what context, with real measured numbers.
FoundationStereo on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 641k | 1453.9-1767.1 t/s | ~38.8-47.1 (slow) |
| Q8 | yes | 646k | 2907.8-3534.1 t/s | ~77.5-94.2 (slow) |
| Q4 | yes | 648k | 5192.6-6311 t/s | ~138.5-168.3 (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 FoundationStereo?▶
Yes. At Q4 it generates ~5192.6-6311 tok/s and fits up to 648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~138.5-168.3 tok/s.
How much context fits?▶
At Q4, up to about 648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.