🔌
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 GMKtec EVO-X3 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 GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1640k | 26.8-32.6 t/s | ~1-1.3 (slow) |
| Q8 | yes | 1688k | 53.7-65.2 t/s | ~2.1-2.5 (slow) |
| Q4 | yes | 1708k | 95.9-116.5 t/s | ~3.7-4.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the GMKtec EVO-X3 run RWKV-6 (Finch) 3B?▶
Yes. At Q4 it generates ~95.9-116.5 tok/s and fits up to 1708k context; beyond that it spills to SSD swap and slows to ~3.7-4.6 tok/s.
How much context fits?▶
At Q4, up to about 1708k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.