🔌
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 CodeT5-base?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-base on the NVIDIA DGX Spark
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1728k | 452.9-539.8 t/s | ~16.6-19.8 (slow) |
| Q8 | yes | 1732k | 905.9-1079.6 t/s | ~33.2-39.5 (slow) |
| Q4 | yes | 1733k | 1617.6-1927.8 t/s | ~59.3-70.6 (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 CodeT5-base?▶
Yes. At Q4 it generates ~1617.6-1927.8 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~59.3-70.6 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.