🔌
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 Qwen-VLA?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-VLA on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 789k | 19.3-23.1 t/s | ~0.7-0.8 (slow) |
| Q8 | yes | 828k | 38.7-46.1 t/s | ~1.4-1.7 (slow) |
| Q4 | yes | 845k | 69.1-82.4 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 Qwen-VLA?▶
Yes. At Q4 it generates ~69.1-82.4 tok/s and fits up to 845k 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 845k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.