// RUN — FITS

Can the GMKtec EVO-X3 run GLM-Z1-Rumination-32B-0414?

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

GLM-Z1-Rumination-32B-0414 on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 190k 2.6-3.2 t/s ~0.1-0.1 (slow)
Q8 yes 312k 5.2-6.3 t/s ~0.2-0.2 (slow)
Q4 yes 365k 9.3-11.3 t/s ~0.4-0.4 (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 → GLM-Z1-Rumination-32B-0414 specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run GLM-Z1-Rumination-32B-0414?▶

Yes. At Q4 it generates ~9.3-11.3 tok/s and fits up to 365k context; beyond that it spills to SSD swap and slows to ~0.4-0.4 tok/s.

How much context fits?▶

At Q4, up to about 365k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.