🔌
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 DistilBERT?
Yes — here's how fast and up to what context, with real measured numbers.
DistilBERT on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1733k | 1260.6-1532.1 t/s | ~49.2-59.8 (slow) |
| Q8 | yes | 1734k | 2521.2-3064.2 t/s | ~98.5-119.7 (slow) |
| Q4 | yes | 1734k | 4502.2-5471.9 t/s | ~175.9-213.7 (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 DistilBERT?▶
Yes. At Q4 it generates ~4502.2-5471.9 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~175.9-213.7 tok/s.
How much context fits?▶
At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.