🔌
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 BiRNA-BERT?
Yes — here's how fast and up to what context, with real measured numbers.
BiRNA-BERT on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 851.7-1015 t/s | ~31.2-37.2 (slow) |
| Q8 | yes | 1733k | 1703.3-2030 t/s | ~62.4-74.4 (slow) |
| Q4 | yes | 1734k | 3041.7-3625 t/s | ~111.4-132.8 (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 BiRNA-BERT?▶
Yes. At Q4 it generates ~3041.7-3625 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~111.4-132.8 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.