// RUN — FITS

Can the GMKtec EVO-X3 run Llama 3.2 3B?

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

Llama 3.2 3B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1637k 25.9-31.5 t/s ~1-1.2 (slow)
Q8 yes 1686k 51.8-63 t/s ~2-2.5 (slow)
Q4 yes 1707k 92.6-112.5 t/s ~3.6-4.4 (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 3B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Llama 3.2 3B?▶

Yes. At Q4 it generates ~92.6-112.5 tok/s and fits up to 1707k context; beyond that it spills to SSD swap and slows to ~3.6-4.4 tok/s.

How much context fits?▶

At Q4, up to about 1707k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.