🔌
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 Minitron 4B?
Yes — here's how fast and up to what context, with real measured numbers.
Minitron 4B on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 69k | 11.9-14.2 t/s | ~0.9-1 (slow) |
| Q8 | yes | 133k | 23.8-28.4 t/s | ~1.7-2.1 (slow) |
| Q4 | yes | 161k | 42.5-50.7 t/s | ~3.1-3.7 (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 Minitron 4B?▶
Yes. At Q4 it generates ~42.5-50.7 tok/s and fits up to 161k context; beyond that it spills to SSD swap and slows to ~3.1-3.7 tok/s.
How much context fits?▶
At Q4, up to about 161k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.