🔌
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 Theseus 6/768?
Yes — here's how fast and up to what context, with real measured numbers.
Theseus 6/768 on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 195k | 757.7-903 t/s | ~55.3-65.9 (slow) |
| Q8 | yes | 196k | 1515.3-1805.9 t/s | ~110.6-131.8 (slow) |
| Q4 | yes | 196k | 2705.9-3224.8 t/s | ~197.5-235.4 (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 Theseus 6/768?▶
Yes. At Q4 it generates ~2705.9-3224.8 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~197.5-235.4 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.