🔌
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 RWKV-6 (Finch) 3B?
Yes — here's how fast and up to what context, with real measured numbers.
RWKV-6 (Finch) 3B on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 102k | 16.1-19.2 t/s | ~1.2-1.4 (slow) |
| Q8 | yes | 150k | 32.3-38.4 t/s | ~2.4-2.8 (slow) |
| Q4 | yes | 170k | 57.6-68.7 t/s | ~4.2-5 (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 RWKV-6 (Finch) 3B?▶
Yes. At Q4 it generates ~57.6-68.7 tok/s and fits up to 170k context; beyond that it spills to SSD swap and slows to ~4.2-5 tok/s.
How much context fits?▶
At Q4, up to about 170k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.