// RUN — FITS

Can the GMKtec EVO-X3 run Typhoon 2.1 Gemma 4B?

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

Typhoon 2.1 Gemma 4B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1613k 20.8-25.3 t/s ~0.8-1 (slow)
Q8 yes 1674k 41.6-50.6 t/s ~1.6-2 (slow)
Q4 yes 1701k 74.3-90.3 t/s ~2.9-3.5 (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 → Typhoon 2.1 Gemma 4B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Typhoon 2.1 Gemma 4B?▶

Yes. At Q4 it generates ~74.3-90.3 tok/s and fits up to 1701k context; beyond that it spills to SSD swap and slows to ~2.9-3.5 tok/s.

How much context fits?▶

At Q4, up to about 1701k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.