🔌
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 Selfish-RNN (SNT-ASGD) Stacked LSTMs?
Yes — here's how fast and up to what context, with real measured numbers.
Selfish-RNN (SNT-ASGD) Stacked LSTMs on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 196k | 1984.3-2364.9 t/s | ~144.8-172.6 (slow) |
| Q8 | yes | 196k | 3968.7-4729.8 t/s | ~289.7-345.2 (slow) |
| Q4 | yes | 197k | 7086.9-8446 t/s | ~517.3-616.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the NVIDIA Jetson T2000
→ Selfish-RNN (SNT-ASGD) Stacked LSTMs specs
→ Other hardware
FAQ
Can the NVIDIA Jetson T2000 run Selfish-RNN (SNT-ASGD) Stacked LSTMs?▶
Yes. At Q4 it generates ~7086.9-8446 tok/s and fits up to 197k context; beyond that it spills to SSD swap and slows to ~517.3-616.5 tok/s.
How much context fits?▶
At Q4, up to about 197k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.