🔌
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 ProtGPT2?
Yes — here's how fast and up to what context, with real measured numbers.
ProtGPT2 on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1712k | 135-160.9 t/s | ~4.9-5.9 (slow) |
| Q8 | yes | 1724k | 270-321.8 t/s | ~9.9-11.8 (slow) |
| Q4 | yes | 1729k | 482.2-574.7 t/s | ~17.7-21.1 (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 ProtGPT2?▶
Yes. At Q4 it generates ~482.2-574.7 tok/s and fits up to 1729k context; beyond that it spills to SSD swap and slows to ~17.7-21.1 tok/s.
How much context fits?▶
At Q4, up to about 1729k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.