🔌
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 ADM?
Yes — here's how fast and up to what context, with real measured numbers.
ADM on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 634k | 872.1-1059.9 t/s | ~23.3-28.3 (slow) |
| Q8 | yes | 642k | 1744.2-2119.9 t/s | ~46.5-56.5 (slow) |
| Q4 | yes | 646k | 3114.6-3785.5 t/s | ~83.1-100.9 (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 ADM?▶
Yes. At Q4 it generates ~3114.6-3785.5 tok/s and fits up to 646k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~83.1-100.9 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.