// RUN — FITS

Can the Apple M3 Max 36GB run T5-3B?

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

T5-3B on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 386k 36.4-43.9 t/s ~1.2-1.5 (slow)
Q8 yes 429k 72.9-87.9 t/s ~2.4-2.9 (slow)
Q4 yes 448k 130.1-156.9 t/s ~4.3-5.2 (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 → T5-3B specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run T5-3B?▶

Yes. At Q4 it generates ~130.1-156.9 tok/s and fits up to 448k context; beyond that it spills to SSD swap and slows to ~4.3-5.2 tok/s.

How much context fits?▶

At Q4, up to about 448k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.