// RUN — FITS

Can the GMKtec EVO-X3 run Pharia-1-LLM-7B?

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

Pharia-1-LLM-7B on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 760k 11.8-14.4 t/s ~0.5-0.6 (slow)
Q8 yes 814k 23.6-28.7 t/s ~0.9-1.1 (slow)
Q4 yes 837k 42.2-51.3 t/s ~1.6-2 (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 → Pharia-1-LLM-7B specs → Other hardware

FAQ

Can the GMKtec EVO-X3 run Pharia-1-LLM-7B?▶

Yes. At Q4 it generates ~42.2-51.3 tok/s and fits up to 837k context; beyond that it spills to SSD swap and slows to ~1.6-2 tok/s.

How much context fits?▶

At Q4, up to about 837k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.