🔌
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 T2000 run Rita-XLarge?
Yes — here's how fast and up to what context, with real measured numbers.
Rita-XLarge on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 160k | 41.7-49.7 t/s | ~3-3.6 (slow) |
| Q8 | yes | 179k | 83.3-99.3 t/s | ~6.1-7.3 (slow) |
| Q4 | yes | 187k | 148.8-177.4 t/s | ~10.9-12.9 (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 T2000 run Rita-XLarge?▶
Yes. At Q4 it generates ~148.8-177.4 tok/s and fits up to 187k context; beyond that it spills to SSD swap and slows to ~10.9-12.9 tok/s.
How much context fits?▶
At Q4, up to about 187k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.