🔌
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 StyleGAN3-T?
Yes — here's how fast and up to what context, with real measured numbers.
StyleGAN3-T on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1735k | 37309.4-45345.3 t/s | ~1457.4-1771.3 (slow) |
| Q8 | yes | 1735k | 74618.8-90690.6 t/s | ~2914.8-3542.6 (slow) |
| Q4 | yes | 1735k | 133247.9-161947.5 t/s | ~5205-6326.1 (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 StyleGAN3-T?▶
Yes. At Q4 it generates ~133247.9-161947.5 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~5205-6326.1 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.