🔌
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 MiniCPM-1.2B?
Yes — here's how fast and up to what context, with real measured numbers.
MiniCPM-1.2B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1697k | 79.9-95.2 t/s | ~2.9-3.5 (slow) |
| Q8 | yes | 1716k | 159.8-190.4 t/s | ~5.9-7 (slow) |
| Q4 | yes | 1724k | 285.3-340 t/s | ~10.4-12.5 (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 MiniCPM-1.2B?▶
Yes. At Q4 it generates ~285.3-340 tok/s and fits up to 1724k context; beyond that it spills to SSD swap and slows to ~10.4-12.5 tok/s.
How much context fits?▶
At Q4, up to about 1724k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.