🔌
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 ALBERT?
Yes — here's how fast and up to what context, with real measured numbers.
ALBERT on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 4622.2-5617.8 t/s | ~180.6-219.4 (slow) |
| Q8 | yes | 1735k | 9244.4-11235.6 t/s | ~361.1-438.9 (slow) |
| Q4 | yes | 1735k | 16507.9-20063.5 t/s | ~644.8-783.7 (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 ALBERT?▶
Yes. At Q4 it generates ~16507.9-20063.5 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~644.8-783.7 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.