🔌
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 Ring-mini-linear-2.0?
Yes — here's how fast and up to what context, with real measured numbers.
Ring-mini-linear-2.0 on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 309k | 6.1-7.2 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 371k | 12.2-14.5 t/s | ~0.4-0.5 (slow) |
| Q4 | yes | 399k | 21.7-25.9 t/s | ~0.8-0.9 (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 Ring-mini-linear-2.0?▶
Yes. At Q4 it generates ~21.7-25.9 tok/s and fits up to 399k context; beyond that it spills to SSD swap and slows to ~0.8-0.9 tok/s.
How much context fits?▶
At Q4, up to about 399k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.