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 StyleGAN3-R?
Yes — here's how fast and up to what context, with real measured numbers.
StyleGAN3-R on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 651k | 308544.3-375000 t/s | ~8227.8-10000 (slow) |
| Q8 | yes | 651k | 617088.6-750000 t/s | ~16455.7-20000 (slow) |
| Q4 | yes | 651k | 1101943.9-1339285.7 t/s | ~29385.2-35714.3 (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 StyleGAN3-R?▶
Yes. At Q4 it generates ~1101943.9-1339285.7 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~29385.2-35714.3 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.