🔌
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 OPT-2.7B (finetuned on PTB)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-2.7B (finetuned on PTB) on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1653k | 30.8-37.5 t/s | ~1.2-1.5 (slow) |
| Q8 | yes | 1694k | 61.6-74.9 t/s | ~2.4-2.9 (slow) |
| Q4 | yes | 1712k | 110.1-133.8 t/s | ~4.3-5.2 (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 OPT-2.7B (finetuned on PTB)?▶
Yes. At Q4 it generates ~110.1-133.8 tok/s and fits up to 1712k context; beyond that it spills to SSD swap and slows to ~4.3-5.2 tok/s.
How much context fits?▶
At Q4, up to about 1712k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.