// RUN — FITS

Can the Apple M3 Max 128GB run Apriel Nemotron 15B?

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

Apriel Nemotron 15B on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 319k 9.1-10.9 t/s ~0.2-0.3 (slow)
Q8 yes 377k 18.1-21.9 t/s ~0.5-0.5 (slow)
Q4 yes 402k 32.4-39 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 M3 Max 128GB → Apriel Nemotron 15B specs → Other hardware

FAQ

Can the Apple M3 Max 128GB run Apriel Nemotron 15B?▶

Yes. At Q4 it generates ~32.4-39 tok/s and fits up to 402k 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 402k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.