🔌
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 CodeT5-large?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-large on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1711k | 108.1-131.3 t/s | ~4.2-5.1 (slow) |
| Q8 | yes | 1723k | 216.1-262.6 t/s | ~8.4-10.3 (slow) |
| Q4 | yes | 1728k | 385.9-469 t/s | ~15.1-18.3 (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 CodeT5-large?▶
Yes. At Q4 it generates ~385.9-469 tok/s and fits up to 1728k context; beyond that it spills to SSD swap and slows to ~15.1-18.3 tok/s.
How much context fits?▶
At Q4, up to about 1728k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.