🔌
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 OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 164k | 46.3-55.2 t/s | ~3.4-4 (slow) |
| Q8 | yes | 180k | 92.6-110.4 t/s | ~6.8-8.1 (slow) |
| Q4 | yes | 188k | 165.4-197.1 t/s | ~12.1-14.4 (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 OpenELM-1.1B?▶
Yes. At Q4 it generates ~165.4-197.1 tok/s and fits up to 188k context; beyond that it spills to SSD swap and slows to ~12.1-14.4 tok/s.
How much context fits?▶
At Q4, up to about 188k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.