// RUN — FITS

Can the Apple M3 Max 128GB run Jamba?

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

Jamba on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 32k 2.6-3.2 t/s ~0.1-0.1 (slow)
Q8 yes 190k 5.3-6.4 t/s ~0.1-0.2 (slow)
Q4 yes 259k 9.4-11.4 t/s ~0.2-0.3 (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 → Jamba specs → Other hardware

FAQ

Can the Apple M3 Max 128GB run Jamba?▶

Yes. At Q4 it generates ~9.4-11.4 tok/s and fits up to 259k context; beyond that it spills to SSD swap and slows to ~0.2-0.3 tok/s.

How much context fits?▶

At Q4, up to about 259k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.