// RUN — FITS

Can the Apple M2 Max 96GB run CausalLM 14B?

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

CausalLM 14B on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 339k 9.3-11.2 t/s ~0.2-0.3 (slow)
Q8 yes 428k 18.5-22.3 t/s ~0.5-0.6 (slow)
Q4 yes 468k 33-39.8 t/s ~0.8-1 (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 → CausalLM 14B specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run CausalLM 14B?▶

Yes. At Q4 it generates ~33-39.8 tok/s and fits up to 468k context; beyond that it spills to SSD swap and slows to ~0.8-1 tok/s.

How much context fits?▶

At Q4, up to about 468k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.