🔌
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 AraELECTRA?
Yes — here's how fast and up to what context, with real measured numbers.
AraELECTRA on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 193k | 367.7-438.2 t/s | ~26.8-32 (slow) |
| Q8 | yes | 195k | 735.4-876.4 t/s | ~53.7-64 (slow) |
| Q4 | yes | 196k | 1313.2-1565 t/s | ~95.9-114.2 (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 T2000 run AraELECTRA?▶
Yes. At Q4 it generates ~1313.2-1565 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~95.9-114.2 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.