🔌
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 Cosmos-Predict2-2B-Text2Image?
Yes — here's how fast and up to what context, with real measured numbers.
Cosmos-Predict2-2B-Text2Image on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 590k | 243.8-296.3 t/s | ~6.5-7.9 (slow) |
| Q8 | yes | 620k | 487.5-592.5 t/s | ~13-15.8 (slow) |
| Q4 | yes | 634k | 870.5-1058 t/s | ~23.2-28.2 (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 Cosmos-Predict2-2B-Text2Image?▶
Yes. At Q4 it generates ~870.5-1058 tok/s and fits up to 634k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~23.2-28.2 tok/s.
How much context fits?▶
At Q4, up to about 634k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.