🔌
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 OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1702k | 92.3-110 t/s | ~3.4-4 (slow) |
| Q8 | yes | 1718k | 184.5-219.9 t/s | ~6.8-8.1 (slow) |
| Q4 | yes | 1726k | 329.5-392.7 t/s | ~12.1-14.4 (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 OpenELM-1.1B?▶
Yes. At Q4 it generates ~329.5-392.7 tok/s and fits up to 1726k context; beyond that it spills to SSD swap and slows to ~12.1-14.4 tok/s.
How much context fits?▶
At Q4, up to about 1726k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.