// RUN — FITS

Can the Apple M4 Max 64GB run Llama 3.2 11B?

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

Llama 3.2 11B on the Apple M4 Max 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 213k 17.5-21.1 t/s ~0.3-0.4 (slow)
Q8 yes 278k 35-42.2 t/s ~0.6-0.8 (slow)
Q4 yes 306k 62.5-75.4 t/s ~1.1-1.4 (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 M4 Max 64GB → Llama 3.2 11B specs → Other hardware

FAQ

Can the Apple M4 Max 64GB run Llama 3.2 11B?▶

Yes. At Q4 it generates ~62.5-75.4 tok/s and fits up to 306k context; beyond that it spills to SSD swap and slows to ~1.1-1.4 tok/s.

How much context fits?▶

At Q4, up to about 306k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.