// RUN — FITS

Can the GMKtec EVO-X3 run DeepSeek-R1-Distill-Qwen-14B?

Yes — here's how fast and up to what context, with real measured numbers.

DeepSeek-R1-Distill-Qwen-14B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 513k 5.6-6.8 t/s ~0.2-0.3 (slow)
Q8 yes 604k 11.2-13.7 t/s ~0.4-0.5 (slow)
Q4 yes 643k 20.1-24.4 t/s ~0.8-1 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

→ All models on the GMKtec EVO-X3 → DeepSeek-R1-Distill-Qwen-14B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run DeepSeek-R1-Distill-Qwen-14B?▶

Yes. At Q4 it generates ~20.1-24.4 tok/s and fits up to 643k context; beyond that it spills to SSD swap and slows to ~0.8-1 tok/s.

How much context fits?▶

At Q4, up to about 643k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.