// RUN — FITS

Can the Apple M2 Max 32GB run Llama Guard?

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

Llama Guard on the Apple M2 Max 32GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 101k 19.4-23.4 t/s ~0.5-0.6 (slow)
Q8 yes 155k 38.9-46.9 t/s ~1-1.2 (slow)
Q4 yes 178k 69.4-83.7 t/s ~1.7-2.1 (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 32GB → Llama Guard specs → Other hardware

FAQ

Can the Apple M2 Max 32GB run Llama Guard?▶

Yes. At Q4 it generates ~69.4-83.7 tok/s and fits up to 178k context; beyond that it spills to SSD swap and slows to ~1.7-2.1 tok/s.

How much context fits?▶

At Q4, up to about 178k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.