// RUN — FITS

Can the Apple M3 Max 128GB run Llama 3.2 90B?

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

Llama 3.2 90B on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 no — — —
Q8 yes 77k 3.1-3.7 t/s ~0.1-0.1 (slow)
Q4 yes 196k 5.5-6.6 t/s ~0.1-0.2 (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 M3 Max 128GB → Llama 3.2 90B specs → Other hardware

FAQ

Can the Apple M3 Max 128GB run Llama 3.2 90B?▶

Yes. At Q4 it generates ~5.5-6.6 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~0.1-0.2 tok/s.

How much context fits?▶

At Q4, up to about 196k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.