// RUN — FITS

Can the Apple M3 Max 36GB run TAPE Transformer?

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

TAPE Transformer on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 470k 2684.2-3236.8 t/s ~89.5-107.9 (slow)
Q8 yes 471k 5368.4-6473.7 t/s ~178.9-215.8 (slow)
Q4 yes 471k 9586.5-11560.2 t/s ~319.5-385.3 (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 M3 Max 36GB → TAPE Transformer specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run TAPE Transformer?▶

Yes. At Q4 it generates ~9586.5-11560.2 tok/s and fits up to 471k context; beyond that it spills to SSD swap and slows to ~319.5-385.3 tok/s.

How much context fits?▶

At Q4, up to about 471k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.