🔌
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 ESM2-8M?
Yes — here's how fast and up to what context, with real measured numbers.
ESM2-8M on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1735k | 12455.6-14844.4 t/s | ~456.3-543.8 (slow) |
| Q8 | yes | 1735k | 24911.3-29688.8 t/s | ~912.5-1087.5 (slow) |
| Q4 | yes | 1735k | 44484.4-53015.6 t/s | ~1629.5-1942 (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 ESM2-8M?▶
Yes. At Q4 it generates ~44484.4-53015.6 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~1629.5-1942 tok/s.
How much context fits?▶
At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.