🔌
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 GPT-2 (774M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (774M) on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1711k | 128.7-153.4 t/s | ~4.7-5.6 (slow) |
| Q8 | yes | 1723k | 257.5-306.9 t/s | ~9.4-11.2 (slow) |
| Q4 | yes | 1728k | 459.8-548 t/s | ~16.8-20.1 (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 GPT-2 (774M)?▶
Yes. At Q4 it generates ~459.8-548 tok/s and fits up to 1728k context; beyond that it spills to SSD swap and slows to ~16.8-20.1 tok/s.
How much context fits?▶
At Q4, up to about 1728k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.