🔌
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 NVIDIA Jetson T3000 run MULAN?
Yes — here's how fast and up to what context, with real measured numbers.
MULAN on the NVIDIA Jetson T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 415k | 2847-3393 t/s | ~104.3-124.3 (slow) |
| Q8 | yes | 416k | 5694-6786 t/s | ~208.6-248.6 (slow) |
| Q4 | yes | 416k | 10167.9-12117.9 t/s | ~372.4-443.9 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA Jetson T3000 run MULAN?▶
Yes. At Q4 it generates ~10167.9-12117.9 tok/s and fits up to 416k context; beyond that it spills to SSD swap and slows to ~372.4-443.9 tok/s.
How much context fits?▶
At Q4, up to about 416k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.