🔌
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 Mamba 2, 2.7B?
Yes — here's how fast and up to what context, with real measured numbers.
Mamba 2, 2.7B on the Jetson Thor T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 114k | 18.5-22.1 t/s | ~1.4-1.6 (slow) |
| Q8 | yes | 156k | 37-44.1 t/s | ~2.7-3.2 (slow) |
| Q4 | yes | 174k | 66.1-78.8 t/s | ~4.8-5.8 (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 Mamba 2, 2.7B?▶
Yes. At Q4 it generates ~66.1-78.8 tok/s and fits up to 174k context; beyond that it spills to SSD swap and slows to ~4.8-5.8 tok/s.
How much context fits?▶
At Q4, up to about 174k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.