🔌
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 DeBERTaV3large?
Yes — here's how fast and up to what context, with real measured numbers.
DeBERTaV3large on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1722k | 199-241.9 t/s | ~7.8-9.4 (slow) |
| Q8 | yes | 1729k | 398.1-483.8 t/s | ~15.6-18.9 (slow) |
| Q4 | yes | 1731k | 710.9-864 t/s | ~27.8-33.7 (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 DeBERTaV3large?▶
Yes. At Q4 it generates ~710.9-864 tok/s and fits up to 1731k context; beyond that it spills to SSD swap and slows to ~27.8-33.7 tok/s.
How much context fits?▶
At Q4, up to about 1731k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.