🔌
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 BigGAN-deep 512x512?
Yes — here's how fast and up to what context, with real measured numbers.
BigGAN-deep 512x512 on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 738.3-897.3 t/s | ~28.8-35.1 (slow) |
| Q8 | yes | 1733k | 1476.6-1794.6 t/s | ~57.7-70.1 (slow) |
| Q4 | yes | 1734k | 2636.7-3204.6 t/s | ~103-125.2 (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 BigGAN-deep 512x512?▶
Yes. At Q4 it generates ~2636.7-3204.6 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~103-125.2 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.