🔌
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 AraBERT LArge v2?
Yes — here's how fast and up to what context, with real measured numbers.
AraBERT LArge v2 on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1724k | 224.3-272.6 t/s | ~8.8-10.6 (slow) |
| Q8 | yes | 1729k | 448.5-545.1 t/s | ~17.5-21.3 (slow) |
| Q4 | yes | 1732k | 800.9-973.4 t/s | ~31.3-38 (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 AraBERT LArge v2?▶
Yes. At Q4 it generates ~800.9-973.4 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~31.3-38 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.