// RUN — FITS

Can the GMKtec EVO-X3 run Llama 3.2 11B?

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

Llama 3.2 11B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 565k 7.8-9.5 t/s ~0.3-0.4 (slow)
Q8 yes 629k 15.7-19.1 t/s ~0.6-0.7 (slow)
Q4 yes 658k 28-34.1 t/s ~1.1-1.3 (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 → Llama 3.2 11B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Llama 3.2 11B?▶

Yes. At Q4 it generates ~28-34.1 tok/s and fits up to 658k context; beyond that it spills to SSD swap and slows to ~1.1-1.3 tok/s.

How much context fits?▶

At Q4, up to about 658k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.