// RUN — FITS

Can the Apple M3 Max 128GB run Granite-4.0-H-Small?

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

Granite-4.0-H-Small on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 190k 4.3-5.1 t/s ~0.1-0.1 (slow)
Q8 yes 312k 8.5-10.3 t/s ~0.2-0.3 (slow)
Q4 yes 365k 15.2-18.3 t/s ~0.4-0.5 (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 → Granite-4.0-H-Small specs → Other hardware

FAQ

Can the Apple M3 Max 128GB run Granite-4.0-H-Small?▶

Yes. At Q4 it generates ~15.2-18.3 tok/s and fits up to 365k context; beyond that it spills to SSD swap and slows to ~0.4-0.5 tok/s.

How much context fits?▶

At Q4, up to about 365k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.