🔌
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 data2vec (language)?
Yes — here's how fast and up to what context, with real measured numbers.
data2vec (language) on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 175k | 70.9-84.5 t/s | ~5.2-6.2 (slow) |
| Q8 | yes | 186k | 141.8-169 t/s | ~10.4-12.3 (slow) |
| Q4 | yes | 191k | 253.3-301.8 t/s | ~18.5-22 (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 data2vec (language)?▶
Yes. At Q4 it generates ~253.3-301.8 tok/s and fits up to 191k context; beyond that it spills to SSD swap and slows to ~18.5-22 tok/s.
How much context fits?▶
At Q4, up to about 191k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.