🔌
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 EmbeddingGemma?
Yes — here's how fast and up to what context, with real measured numbers.
EmbeddingGemma on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1726k | 323.5-385.6 t/s | ~11.9-14.1 (slow) |
| Q8 | yes | 1730k | 647-771.1 t/s | ~23.7-28.2 (slow) |
| Q4 | yes | 1732k | 1155.4-1377 t/s | ~42.3-50.4 (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 EmbeddingGemma?▶
Yes. At Q4 it generates ~1155.4-1377 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~42.3-50.4 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.