🔌
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 Routing Transformer (WT-103)?
Yes — here's how fast and up to what context, with real measured numbers.
Routing Transformer (WT-103) on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 194k | 629-749.6 t/s | ~45.9-54.7 (slow) |
| Q8 | yes | 196k | 1258-1499.2 t/s | ~91.8-109.4 (slow) |
| Q4 | yes | 196k | 2246.4-2677.2 t/s | ~164-195.4 (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 Routing Transformer (WT-103)?▶
Yes. At Q4 it generates ~2246.4-2677.2 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~164-195.4 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.