🔌
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 DiT-XL/2?
Yes — here's how fast and up to what context, with real measured numbers.
DiT-XL/2 on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1714k | 147.6-175.9 t/s | ~5.4-6.4 (slow) |
| Q8 | yes | 1725k | 295.2-351.9 t/s | ~10.8-12.9 (slow) |
| Q4 | yes | 1729k | 527.2-628.3 t/s | ~19.3-23 (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 DiT-XL/2?▶
Yes. At Q4 it generates ~527.2-628.3 tok/s and fits up to 1729k context; beyond that it spills to SSD swap and slows to ~19.3-23 tok/s.
How much context fits?▶
At Q4, up to about 1729k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.