🔌
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 ProBERTa?
Yes — here's how fast and up to what context, with real measured numbers.
ProBERTa on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 1890.9-2298.2 t/s | ~73.9-89.8 (slow) |
| Q8 | yes | 1734k | 3781.8-4596.4 t/s | ~147.7-179.5 (slow) |
| Q4 | yes | 1735k | 6753.2-8207.8 t/s | ~263.8-320.6 (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 ProBERTa?▶
Yes. At Q4 it generates ~6753.2-8207.8 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~263.8-320.6 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.