🔌
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 ProtGPT2?
Yes — here's how fast and up to what context, with real measured numbers.
ProtGPT2 on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 174k | 67.8-80.8 t/s | ~4.9-5.9 (slow) |
| Q8 | yes | 186k | 135.5-161.5 t/s | ~9.9-11.8 (slow) |
| Q4 | yes | 191k | 242-288.4 t/s | ~17.7-21.1 (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 ProtGPT2?▶
Yes. At Q4 it generates ~242-288.4 tok/s and fits up to 191k context; beyond that it spills to SSD swap and slows to ~17.7-21.1 tok/s.
How much context fits?▶
At Q4, up to about 191k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.