🔌
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 ESM3-open-small?
Yes — here's how fast and up to what context, with real measured numbers.
ESM3-open-small on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1692k | 71.2-84.8 t/s | ~2.6-3.1 (slow) |
| Q8 | yes | 1714k | 142.4-169.7 t/s | ~5.2-6.2 (slow) |
| Q4 | yes | 1723k | 254.2-302.9 t/s | ~9.3-11.1 (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 ESM3-open-small?▶
Yes. At Q4 it generates ~254.2-302.9 tok/s and fits up to 1723k context; beyond that it spills to SSD swap and slows to ~9.3-11.1 tok/s.
How much context fits?▶
At Q4, up to about 1723k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.