🔌
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 T2000 run DeciLM 6B?
Yes — here's how fast and up to what context, with real measured numbers.
DeciLM 6B on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 11k | 8.8-10.5 t/s | ~0.6-0.8 (slow) |
| Q8 | yes | 55k | 17.5-20.9 t/s | ~1.3-1.5 (slow) |
| Q4 | yes | 74k | 31.3-37.3 t/s | ~2.3-2.7 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA Jetson T2000 run DeciLM 6B?▶
Yes. At Q4 it generates ~31.3-37.3 tok/s and fits up to 74k context; beyond that it spills to SSD swap and slows to ~2.3-2.7 tok/s.
How much context fits?▶
At Q4, up to about 74k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.