// RUN — FITS

Can the Apple M1 Max 32GB run Granite Vision 3.2 2B?

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

Granite Vision 3.2 2B on the Apple M1 Max 32GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 326k 45.6-55 t/s ~1.1-1.4 (slow)
Q8 yes 371k 91.3-110.1 t/s ~2.3-2.8 (slow)
Q4 yes 391k 163-196.5 t/s ~4.1-4.9 (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 M1 Max 32GB → Granite Vision 3.2 2B specs → Other hardware

FAQ

Can the Apple M1 Max 32GB run Granite Vision 3.2 2B?▶

Yes. At Q4 it generates ~163-196.5 tok/s and fits up to 391k context; beyond that it spills to SSD swap and slows to ~4.1-4.9 tok/s.

How much context fits?▶

At Q4, up to about 391k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.