🔌
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 MSA Transformer?
Yes — here's how fast and up to what context, with real measured numbers.
MSA Transformer on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1732k | 996.5-1187.6 t/s | ~36.5-43.5 (slow) |
| Q8 | yes | 1733k | 1992.9-2375.1 t/s | ~73-87 (slow) |
| Q4 | yes | 1734k | 3558.8-4241.3 t/s | ~130.4-155.4 (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 MSA Transformer?▶
Yes. At Q4 it generates ~3558.8-4241.3 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~130.4-155.4 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.