// RUN — FITS

Can the GMKtec EVO-X3 run Llama 3.2 1B?

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

Llama 3.2 1B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1697k 67.6-82.2 t/s ~2.6-3.2 (slow)
Q8 yes 1716k 135.3-164.4 t/s ~5.3-6.4 (slow)
Q4 yes 1724k 241.6-293.6 t/s ~9.4-11.5 (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 1B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Llama 3.2 1B?▶

Yes. At Q4 it generates ~241.6-293.6 tok/s and fits up to 1724k context; beyond that it spills to SSD swap and slows to ~9.4-11.5 tok/s.

How much context fits?▶

At Q4, up to about 1724k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.