🔌
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 NVIDIA DGX Spark run Stable Cascade?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Cascade on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 789k | 19.5-23.2 t/s | ~0.7-0.8 (slow) |
| Q8 | yes | 828k | 38.9-46.4 t/s | ~1.4-1.7 (slow) |
| Q4 | yes | 846k | 69.5-82.8 t/s | ~2.5-3 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA DGX Spark run Stable Cascade?▶
Yes. At Q4 it generates ~69.5-82.8 tok/s and fits up to 846k context; beyond that it spills to SSD swap and slows to ~2.5-3 tok/s.
How much context fits?▶
At Q4, up to about 846k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.