// RUN โ€” FITS

Can the GMKtec EVO-X3 run ESM1-85M?

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

ESM1-85M on the GMKtec EVO-X3

QuantFits?Max contextSpeedBeyond context
FP16 yes 1732k 977.7-1188.2 t/s ~38.2-46.4 (slow)
Q8 yes 1734k 1955.3-2376.5 t/s ~76.4-92.8 (slow)
Q4 yes 1734k 3491.7-4243.7 t/s ~136.4-165.8 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the GMKtec EVO-X3 run ESM1-85M?โ–ถ

Yes. At Q4 it generates ~3491.7-4243.7 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~136.4-165.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.