🔌
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 ERNIE-4.5-0.3B?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-4.5-0.3B on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1724k | 276.8-329.9 t/s | ~10.1-12.1 (slow) |
| Q8 | yes | 1729k | 553.6-659.8 t/s | ~20.3-24.2 (slow) |
| Q4 | yes | 1732k | 988.5-1178.1 t/s | ~36.2-43.2 (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 ERNIE-4.5-0.3B?▶
Yes. At Q4 it generates ~988.5-1178.1 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~36.2-43.2 tok/s.
How much context fits?▶
At Q4, up to about 1732k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.