// RUN — FITS

Can the Apple M2 Max 96GB run Routing Transformer (WT-103)?

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

Routing Transformer (WT-103) on the Apple M2 Max 96GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1293k 1710.7-2062.9 t/s ~42.8-51.6 (slow)
Q8 yes 1294k 3421.4-4125.8 t/s ~85.5-103.1 (slow)
Q4 yes 1295k 6109.6-7367.5 t/s ~152.7-184.2 (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 M2 Max 96GB → Routing Transformer (WT-103) specs → Other hardware

FAQ

Can the Apple M2 Max 96GB run Routing Transformer (WT-103)?▶

Yes. At Q4 it generates ~6109.6-7367.5 tok/s and fits up to 1295k context; beyond that it spills to SSD swap and slows to ~152.7-184.2 tok/s.

How much context fits?▶

At Q4, up to about 1295k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.