🔌
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 BART-IT?
Yes — here's how fast and up to what context, with real measured numbers.
BART-IT on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 193k | 357.2-425.7 t/s | ~26.1-31.1 (slow) |
| Q8 | yes | 195k | 714.4-851.4 t/s | ~52.1-62.1 (slow) |
| Q4 | yes | 196k | 1275.6-1520.3 t/s | ~93.1-111 (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 BART-IT?▶
Yes. At Q4 it generates ~1275.6-1520.3 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~93.1-111 tok/s.
How much context fits?▶
At Q4, up to about 196k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.