// RUN — FITS

Can the Apple M3 Max 36GB run Stable Cascade?

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

Stable Cascade on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 158k 19.9-24 t/s ~0.7-0.8 (slow)
Q8 yes 197k 39.8-48 t/s ~1.3-1.6 (slow)
Q4 yes 214k 71.1-85.8 t/s ~2.4-2.9 (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 36GB → Stable Cascade specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run Stable Cascade?▶

Yes. At Q4 it generates ~71.1-85.8 tok/s and fits up to 214k context; beyond that it spills to SSD swap and slows to ~2.4-2.9 tok/s.

How much context fits?▶

At Q4, up to about 214k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.