🔌
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 Segatron XL base, M=384?
Yes — here's how fast and up to what context, with real measured numbers.
Segatron XL base, M=384 on the Jetson Thor T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 409k | 387.7-462.1 t/s | ~14.2-16.9 (slow) |
| Q8 | yes | 413k | 775.4-924.2 t/s | ~28.4-33.9 (slow) |
| Q4 | yes | 414k | 1384.7-1650.3 t/s | ~50.7-60.5 (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 Segatron XL base, M=384?▶
Yes. At Q4 it generates ~1384.7-1650.3 tok/s and fits up to 414k context; beyond that it spills to SSD swap and slows to ~50.7-60.5 tok/s.
How much context fits?▶
At Q4, up to about 414k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.