// RUN — FITS

Can the Apple M2 Max 96GB run EXAONE 4.0 (1.2B)?

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

EXAONE 4.0 (1.2B) on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1259k 113.3-136.7 t/s ~2.8-3.4 (slow)
Q8 yes 1277k 226.7-273.3 t/s ~5.7-6.8 (slow)
Q4 yes 1285k 404.8-488.1 t/s ~10.1-12.2 (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 Apple M2 Max 96GB → EXAONE 4.0 (1.2B) specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run EXAONE 4.0 (1.2B)?▶

Yes. At Q4 it generates ~404.8-488.1 tok/s and fits up to 1285k context; beyond that it spills to SSD swap and slows to ~10.1-12.2 tok/s.

How much context fits?▶

At Q4, up to about 1285k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.