// RUN โ€” FITS

Can the Apple M4 Max 48GB run Surya?

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

Surya on the Apple M4 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 625k 507.2-611.6 t/s ~9.3-11.2 (slow)
Q8 yes 631k 1014.4-1223.3 t/s ~18.6-22.4 (slow)
Q4 yes 633k 1811.5-2184.4 t/s ~33.2-40 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the Apple M4 Max 48GB run Surya?โ–ถ

Yes. At Q4 it generates ~1811.5-2184.4 tok/s and fits up to 633k context; beyond that it spills to SSD swap and slows to ~33.2-40 tok/s.

How much context fits?โ–ถ

At Q4, up to about 633k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.