// RUN — FITS

Can the GMKtec EVO-X3 run Japanese-LM-3.6B?

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

Japanese-LM-3.6B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1625k 23.1-28.1 t/s ~0.9-1.1 (slow)
Q8 yes 1680k 46.2-56.2 t/s ~1.8-2.2 (slow)
Q4 yes 1704k 82.5-100.3 t/s ~3.2-3.9 (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 → Japanese-LM-3.6B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Japanese-LM-3.6B?▶

Yes. At Q4 it generates ~82.5-100.3 tok/s and fits up to 1704k context; beyond that it spills to SSD swap and slows to ~3.2-3.9 tok/s.

How much context fits?▶

At Q4, up to about 1704k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.