🔌
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 TrellisNet-MoS (1.4x larger) PTB?
Yes — here's how fast and up to what context, with real measured numbers.
TrellisNet-MoS (1.4x larger) PTB on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 2930.7-3492.8 t/s | ~107.4-127.9 (slow) |
| Q8 | yes | 1734k | 5861.5-6985.6 t/s | ~214.7-255.9 (slow) |
| Q4 | yes | 1735k | 10466.9-12474.3 t/s | ~383.4-456.9 (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 TrellisNet-MoS (1.4x larger) PTB?▶
Yes. At Q4 it generates ~10466.9-12474.3 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~383.4-456.9 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.