// RUN — FITS

Can the Apple M4 Max 48GB run GLA Transformer 1.3B?

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

GLA Transformer 1.3B on the Apple M4 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 597k 142.8-172.2 t/s ~2.6-3.2 (slow)
Q8 yes 616k 285.6-344.4 t/s ~5.2-6.3 (slow)
Q4 yes 625k 510-615 t/s ~9.3-11.3 (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 M4 Max 48GB → GLA Transformer 1.3B specs → Other hardware

FAQ

Can the Apple M4 Max 48GB run GLA Transformer 1.3B?▶

Yes. At Q4 it generates ~510-615 tok/s and fits up to 625k context; beyond that it spills to SSD swap and slows to ~9.3-11.3 tok/s.

How much context fits?▶

At Q4, up to about 625k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.