🔌
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 Tensor-Transformer(1core)+PN (WT103)?
Yes — here's how fast and up to what context, with real measured numbers.
Tensor-Transformer(1core)+PN (WT103) on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1732k | 1168.2-1392.2 t/s | ~42.8-51 (slow) |
| Q8 | yes | 1734k | 2336.3-2784.4 t/s | ~85.6-102 (slow) |
| Q4 | yes | 1734k | 4172-4972.2 t/s | ~152.8-182.1 (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 Tensor-Transformer(1core)+PN (WT103)?▶
Yes. At Q4 it generates ~4172-4972.2 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~152.8-182.1 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.