// RUN — FITS

Can the Apple M3 Max 48GB run Gemma2 9B CPT Sahabat-AI?

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

Gemma2 9B CPT Sahabat-AI on the Apple M3 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 181k 15.1-18.2 t/s ~0.4-0.5 (slow)
Q8 yes 249k 30.2-36.4 t/s ~0.8-0.9 (slow)
Q4 yes 280k 54-65.1 t/s ~1.3-1.6 (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 M3 Max 48GB → Gemma2 9B CPT Sahabat-AI specs → Other hardware

FAQ

Can the Apple M3 Max 48GB run Gemma2 9B CPT Sahabat-AI?▶

Yes. At Q4 it generates ~54-65.1 tok/s and fits up to 280k context; beyond that it spills to SSD swap and slows to ~1.3-1.6 tok/s.

How much context fits?▶

At Q4, up to about 280k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.