// RUN — FITS

Can the GMKtec EVO-X3 run Segatron XL large, M=384?

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

Segatron XL large, M=384 on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1727k 323.7-393.5 t/s ~12.6-15.4 (slow)
Q8 yes 1731k 647.5-786.9 t/s ~25.3-30.7 (slow)
Q4 yes 1733k 1156.2-1405.2 t/s ~45.2-54.9 (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 → Segatron XL large, M=384 specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Segatron XL large, M=384?▶

Yes. At Q4 it generates ~1156.2-1405.2 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~45.2-54.9 tok/s.

How much context fits?▶

At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.