🔌
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 Jetson T3000 run VILA1.5-13B?
Yes — here's how fast and up to what context, with real measured numbers.
VILA1.5-13B on the NVIDIA Jetson T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2k | 7.4-8.8 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 84k | 14.8-17.6 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 121k | 26.4-31.4 t/s | ~1-1.2 (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 Jetson T3000 run VILA1.5-13B?▶
Yes. At Q4 it generates ~26.4-31.4 tok/s and fits up to 121k context; beyond that it spills to SSD swap and slows to ~1-1.2 tok/s.
How much context fits?▶
At Q4, up to about 121k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.