🔌
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-Neo-125M?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-Neo-125M on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 797.2-950 t/s | ~29.2-34.8 (slow) |
| Q8 | yes | 1733k | 1594.3-1900.1 t/s | ~58.4-69.6 (slow) |
| Q4 | yes | 1734k | 2847-3393 t/s | ~104.3-124.3 (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-Neo-125M?▶
Yes. At Q4 it generates ~2847-3393 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~104.3-124.3 tok/s.
How much context fits?▶
At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.