🔌
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 German ELECTRA Large?
Yes — here's how fast and up to what context, with real measured numbers.
German ELECTRA Large on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1725k | 248.4-301.9 t/s | ~9.7-11.8 (slow) |
| Q8 | yes | 1730k | 496.7-603.7 t/s | ~19.4-23.6 (slow) |
| Q4 | yes | 1732k | 887-1078 t/s | ~34.6-42.1 (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 German ELECTRA Large?▶
Yes. At Q4 it generates ~887-1078 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~34.6-42.1 tok/s.
How much context fits?▶
At Q4, up to about 1732k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.