🔌
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 T3000 run ERNIE 3.0?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE 3.0 on the Jetson Thor T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 45k | 10-11.9 t/s | ~0.4-0.4 (slow) |
| Q8 | yes | 106k | 19.9-23.8 t/s | ~0.7-0.9 (slow) |
| Q4 | yes | 132k | 35.6-42.4 t/s | ~1.3-1.6 (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 T3000 run ERNIE 3.0?▶
Yes. At Q4 it generates ~35.6-42.4 tok/s and fits up to 132k context; beyond that it spills to SSD swap and slows to ~1.3-1.6 tok/s.
How much context fits?▶
At Q4, up to about 132k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.