// RUN — FITS

Can the Apple M3 Max 36GB run CRYSTALCODER?

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

CRYSTALCODER on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 134k 15.2-18.4 t/s ~0.5-0.6 (slow)
Q8 yes 185k 30.4-36.7 t/s ~1-1.2 (slow)
Q4 yes 207k 54.4-65.6 t/s ~1.8-2.2 (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 → CRYSTALCODER specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run CRYSTALCODER?▶

Yes. At Q4 it generates ~54.4-65.6 tok/s and fits up to 207k context; beyond that it spills to SSD swap and slows to ~1.8-2.2 tok/s.

How much context fits?▶

At Q4, up to about 207k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.