🔌
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 nesso 0.4B Agentic?
Yes — here's how fast and up to what context, with real measured numbers.
nesso 0.4B Agentic on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 185k | 125-149 t/s | ~9.1-10.9 (slow) |
| Q8 | yes | 191k | 250-298 t/s | ~18.3-21.8 (slow) |
| Q4 | yes | 193k | 446.5-532.1 t/s | ~32.6-38.8 (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 nesso 0.4B Agentic?▶
Yes. At Q4 it generates ~446.5-532.1 tok/s and fits up to 193k context; beyond that it spills to SSD swap and slows to ~32.6-38.8 tok/s.
How much context fits?▶
At Q4, up to about 193k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.