🔌
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 OPT-125M (finetuned)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-125M (finetuned) on the Jetson Thor T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 413k | 797.2-950 t/s | ~29.2-34.8 (slow) |
| Q8 | yes | 415k | 1594.3-1900.1 t/s | ~58.4-69.6 (slow) |
| Q4 | yes | 415k | 2847-3393 t/s | ~104.3-124.3 (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 OPT-125M (finetuned)?▶
Yes. At Q4 it generates ~2847-3393 tok/s and fits up to 415k context; beyond that it spills to SSD swap and slows to ~104.3-124.3 tok/s.
How much context fits?▶
At Q4, up to about 415k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.