// RUN — FITS

Can the Apple M2 Max 96GB run Llama 3.2 3B?

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

Llama 3.2 3B on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1198k 42.4-51.1 t/s ~1.1-1.3 (slow)
Q8 yes 1246k 84.7-102.2 t/s ~2.1-2.6 (slow)
Q4 yes 1268k 151.3-182.5 t/s ~3.8-4.6 (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 → Llama 3.2 3B specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run Llama 3.2 3B?▶

Yes. At Q4 it generates ~151.3-182.5 tok/s and fits up to 1268k context; beyond that it spills to SSD swap and slows to ~3.8-4.6 tok/s.

How much context fits?▶

At Q4, up to about 1268k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.