🔌
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 StableLM-2-1.6B?
Yes — here's how fast and up to what context, with real measured numbers.
StableLM-2-1.6B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1685k | 60.6-72.2 t/s | ~2.2-2.6 (slow) |
| Q8 | yes | 1710k | 121.2-144.4 t/s | ~4.4-5.3 (slow) |
| Q4 | yes | 1721k | 216.4-257.9 t/s | ~7.9-9.4 (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 StableLM-2-1.6B?▶
Yes. At Q4 it generates ~216.4-257.9 tok/s and fits up to 1721k context; beyond that it spills to SSD swap and slows to ~7.9-9.4 tok/s.
How much context fits?▶
At Q4, up to about 1721k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.