🔌
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 Qwen3-0.6B?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen3-0.6B on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 179k | 83.3-99.3 t/s | ~6.1-7.3 (slow) |
| Q8 | yes | 188k | 166.7-198.7 t/s | ~12.2-14.5 (slow) |
| Q4 | yes | 192k | 297.6-354.7 t/s | ~21.7-25.9 (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 Qwen3-0.6B?▶
Yes. At Q4 it generates ~297.6-354.7 tok/s and fits up to 192k context; beyond that it spills to SSD swap and slows to ~21.7-25.9 tok/s.
How much context fits?▶
At Q4, up to about 192k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.