🔌
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 ERNIE-Doc (247M)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc (247M) on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1727k | 336.8-409.4 t/s | ~13.2-16 (slow) |
| Q8 | yes | 1731k | 673.7-818.8 t/s | ~26.3-32 (slow) |
| Q4 | yes | 1733k | 1203-1462.1 t/s | ~47-57.1 (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 ERNIE-Doc (247M)?▶
Yes. At Q4 it generates ~1203-1462.1 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~47-57.1 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.