🔌
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 Pangu-Weather?
Yes — here's how fast and up to what context, with real measured numbers.
Pangu-Weather on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1727k | 325-395 t/s | ~12.7-15.4 (slow) |
| Q8 | yes | 1731k | 650-790 t/s | ~25.4-30.9 (slow) |
| Q4 | yes | 1733k | 1160.7-1410.7 t/s | ~45.3-55.1 (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 Pangu-Weather?▶
Yes. At Q4 it generates ~1160.7-1410.7 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~45.3-55.1 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.