🔌
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 Qwen2.5 Instruct (7B)?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen2.5 Instruct (7B) on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 751k | 13.1-15.6 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 809k | 26.2-31.2 t/s | ~1-1.1 (slow) |
| Q4 | yes | 835k | 46.8-55.7 t/s | ~1.7-2 (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 Qwen2.5 Instruct (7B)?▶
Yes. At Q4 it generates ~46.8-55.7 tok/s and fits up to 835k context; beyond that it spills to SSD swap and slows to ~1.7-2 tok/s.
How much context fits?▶
At Q4, up to about 835k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.