🔌
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-VL?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-VL on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 721k | 10.4-12.4 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 794k | 20.8-24.7 t/s | ~0.8-0.9 (slow) |
| Q4 | yes | 826k | 37.1-44.2 t/s | ~1.4-1.6 (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-VL?▶
Yes. At Q4 it generates ~37.1-44.2 tok/s and fits up to 826k context; beyond that it spills to SSD swap and slows to ~1.4-1.6 tok/s.
How much context fits?▶
At Q4, up to about 826k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.