🔌
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 Genie 2 (bio)?
Yes — here's how fast and up to what context, with real measured numbers.
Genie 2 (bio) on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 6346.8-7564 t/s | ~232.5-277.1 (slow) |
| Q8 | yes | 1735k | 12693.6-15128 t/s | ~465-554.1 (slow) |
| Q4 | yes | 1735k | 22667.2-27014.3 t/s | ~830.3-989.5 (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 Genie 2 (bio)?▶
Yes. At Q4 it generates ~22667.2-27014.3 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~830.3-989.5 tok/s.
How much context fits?▶
At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.