// RUN — FITS

Can the GMKtec EVO-X3 run DiffusionGemma 26B-A4B?

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

DiffusionGemma 26B-A4B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 235k 3.2-3.9 t/s ~0.1-0.2 (slow)
Q8 yes 335k 6.4-7.8 t/s ~0.3-0.3 (slow)
Q4 yes 378k 11.4-13.9 t/s ~0.4-0.5 (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 → DiffusionGemma 26B-A4B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run DiffusionGemma 26B-A4B?▶

Yes. At Q4 it generates ~11.4-13.9 tok/s and fits up to 378k context; beyond that it spills to SSD swap and slows to ~0.4-0.5 tok/s.

How much context fits?▶

At Q4, up to about 378k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.