🔌
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 Kimi Linear?
Yes — here's how fast and up to what context, with real measured numbers.
Kimi Linear on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 54k | 2.1-2.5 t/s | ~0.1-0.1 (slow) |
| Q8 | yes | 201k | 4.2-4.9 t/s | ~0.2-0.2 (slow) |
| Q4 | yes | 265k | 7.4-8.8 t/s | ~0.3-0.3 (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 Kimi Linear?▶
Yes. At Q4 it generates ~7.4-8.8 tok/s and fits up to 265k context; beyond that it spills to SSD swap and slows to ~0.3-0.3 tok/s.
How much context fits?▶
At Q4, up to about 265k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.