🔌
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 DiT-XL/2?
Yes — here's how fast and up to what context, with real measured numbers.
DiT-XL/2 on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 630k | 722.2-877.8 t/s | ~19.3-23.4 (slow) |
| Q8 | yes | 641k | 1444.4-1755.6 t/s | ~38.5-46.8 (slow) |
| Q4 | yes | 645k | 2579.4-3134.9 t/s | ~68.8-83.6 (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 DiT-XL/2?▶
Yes. At Q4 it generates ~2579.4-3134.9 tok/s and fits up to 645k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~68.8-83.6 tok/s.
How much context fits?▶
At Q4, up to about 645k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.