🔌
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 Qwen2-0.5B?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen2-0.5B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1720k | 199.3-237.5 t/s | ~7.3-8.7 (slow) |
| Q8 | yes | 1727k | 398.6-475 t/s | ~14.6-17.4 (slow) |
| Q4 | yes | 1731k | 711.8-848.3 t/s | ~26.1-31.1 (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 Qwen2-0.5B?▶
Yes. At Q4 it generates ~711.8-848.3 tok/s and fits up to 1731k context; beyond that it spills to SSD swap and slows to ~26.1-31.1 tok/s.
How much context fits?▶
At Q4, up to about 1731k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.