// RUN — FITS

Can the Apple M2 Max 96GB run Mistral Small 3?

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

Mistral Small 3 on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 141k 5.7-6.8 t/s ~0.1-0.2 (slow)
Q8 yes 232k 11.3-13.7 t/s ~0.3-0.3 (slow)
Q4 yes 273k 20.2-24.4 t/s ~0.5-0.6 (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 96GB → Mistral Small 3 specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run Mistral Small 3?▶

Yes. At Q4 it generates ~20.2-24.4 tok/s and fits up to 273k context; beyond that it spills to SSD swap and slows to ~0.5-0.6 tok/s.

How much context fits?▶

At Q4, up to about 273k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.