// RUN — FITS

Can the Apple M4 Max 36GB run Llama 3.2 1B?

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

Llama 3.2 1B on the Apple M4 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 434k 150.9-182 t/s ~2.8-3.3 (slow)
Q8 yes 453k 301.9-364 t/s ~5.5-6.7 (slow)
Q4 yes 461k 539-650 t/s ~9.9-11.9 (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 36GB → Llama 3.2 1B specs → Other hardware

FAQ

Can the Apple M4 Max 36GB run Llama 3.2 1B?▶

Yes. At Q4 it generates ~539-650 tok/s and fits up to 461k context; beyond that it spills to SSD swap and slows to ~9.9-11.9 tok/s.

How much context fits?▶

At Q4, up to about 461k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.