🔌
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 CogVLM-17B?
Yes — here's how fast and up to what context, with real measured numbers.
CogVLM-17B on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 304k | 4.9-5.9 t/s | ~0.2-0.2 (slow) |
| Q8 | yes | 369k | 9.8-11.9 t/s | ~0.4-0.5 (slow) |
| Q4 | yes | 397k | 17.5-21.2 t/s | ~0.7-0.8 (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 CogVLM-17B?▶
Yes. At Q4 it generates ~17.5-21.2 tok/s and fits up to 397k context; beyond that it spills to SSD swap and slows to ~0.7-0.8 tok/s.
How much context fits?▶
At Q4, up to about 397k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.