🔌
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 GPT-1?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-1 on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 193k | 427.4-509.4 t/s | ~31.2-37.2 (slow) |
| Q8 | yes | 195k | 854.8-1018.7 t/s | ~62.4-74.4 (slow) |
| Q4 | yes | 196k | 1526.4-1819.1 t/s | ~111.4-132.8 (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 GPT-1?▶
Yes. At Q4 it generates ~1526.4-1819.1 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~111.4-132.8 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.