🔌
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 GPT-2 (124M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (124M) on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 671-815.5 t/s | ~26.2-31.9 (slow) |
| Q8 | yes | 1733k | 1341.9-1631 t/s | ~52.4-63.7 (slow) |
| Q4 | yes | 1734k | 2396.3-2912.4 t/s | ~93.6-113.8 (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 GPT-2 (124M)?▶
Yes. At Q4 it generates ~2396.3-2912.4 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~93.6-113.8 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.