🔌
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 AWD-LSTM-DOC (fin) (23M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (23M) on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 3617.4-4396.5 t/s | ~141.3-171.7 (slow) |
| Q8 | yes | 1735k | 7234.8-8793 t/s | ~282.6-343.5 (slow) |
| Q4 | yes | 1735k | 12919.3-15701.9 t/s | ~504.7-613.4 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the GMKtec EVO-X3 run AWD-LSTM-DOC (fin) (23M)?▶
Yes. At Q4 it generates ~12919.3-15701.9 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~504.7-613.4 tok/s.
How much context fits?▶
At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.