🔌
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 UDSMProt?
Yes — here's how fast and up to what context, with real measured numbers.
UDSMProt on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 196k | 1766.7-2105.5 t/s | ~129-153.7 (slow) |
| Q8 | yes | 196k | 3533.4-4211.1 t/s | ~257.9-307.4 (slow) |
| Q4 | yes | 197k | 6309.7-7519.8 t/s | ~460.6-548.9 (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 UDSMProt?▶
Yes. At Q4 it generates ~6309.7-7519.8 tok/s and fits up to 197k context; beyond that it spills to SSD swap and slows to ~460.6-548.9 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.