🔌
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 Granite 3.2 2B?
Yes — here's how fast and up to what context, with real measured numbers.
Granite 3.2 2B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1658k | 39.4-46.9 t/s | ~1.4-1.7 (slow) |
| Q8 | yes | 1696k | 78.8-93.9 t/s | ~2.9-3.4 (slow) |
| Q4 | yes | 1713k | 140.7-167.6 t/s | ~5.2-6.1 (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 Granite 3.2 2B?▶
Yes. At Q4 it generates ~140.7-167.6 tok/s and fits up to 1713k context; beyond that it spills to SSD swap and slows to ~5.2-6.1 tok/s.
How much context fits?▶
At Q4, up to about 1713k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.