🔌
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 AWD-LSTM-DOC (fin) (37M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (37M) on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 2693.1-3209.6 t/s | ~98.6-117.6 (slow) |
| Q8 | yes | 1734k | 5386.2-6419.2 t/s | ~197.3-235.1 (slow) |
| Q4 | yes | 1735k | 9618.2-11462.8 t/s | ~352.3-419.9 (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 AWD-LSTM-DOC (fin) (37M)?▶
Yes. At Q4 it generates ~9618.2-11462.8 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~352.3-419.9 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.