🔌
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 InternVL2_5-26B?
Yes — here's how fast and up to what context, with real measured numbers.
InternVL2_5-26B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 239k | 3.9-4.7 t/s | ~0.1-0.2 (slow) |
| Q8 | yes | 336k | 7.8-9.3 t/s | ~0.3-0.3 (slow) |
| Q4 | yes | 379k | 14-16.6 t/s | ~0.5-0.6 (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 InternVL2_5-26B?▶
Yes. At Q4 it generates ~14-16.6 tok/s and fits up to 379k context; beyond that it spills to SSD swap and slows to ~0.5-0.6 tok/s.
How much context fits?▶
At Q4, up to about 379k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.