🔌
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 Jetson Thor T2000 run TiTok-L?
Yes — here's how fast and up to what context, with real measured numbers.
TiTok-L on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 187k | 162.9-194.1 t/s | ~11.9-14.2 (slow) |
| Q8 | yes | 192k | 325.8-388.2 t/s | ~23.8-28.3 (slow) |
| Q4 | yes | 194k | 581.7-693.3 t/s | ~42.5-50.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the Jetson Thor T2000 run TiTok-L?▶
Yes. At Q4 it generates ~581.7-693.3 tok/s and fits up to 194k context; beyond that it spills to SSD swap and slows to ~42.5-50.6 tok/s.
How much context fits?▶
At Q4, up to about 194k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.