🔌
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 code2seq?
Yes — here's how fast and up to what context, with real measured numbers.
code2seq on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1734k | 2248.6-2733 t/s | ~87.8-106.8 (slow) |
| Q8 | yes | 1734k | 4497.3-5465.9 t/s | ~175.7-213.5 (slow) |
| Q4 | yes | 1735k | 8030.9-9760.6 t/s | ~313.7-381.3 (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 code2seq?▶
Yes. At Q4 it generates ~8030.9-9760.6 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~313.7-381.3 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.