// RUN — FITS

Can the Apple M3 Max 36GB run Qwen3-14B?

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

Qwen3-14B on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 8k 6.9-8.3 t/s ~0.2-0.3 (slow)
Q8 yes 98k 13.8-16.6 t/s ~0.5-0.6 (slow)
Q4 yes 138k 24.6-29.7 t/s ~0.8-1 (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 → Qwen3-14B specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run Qwen3-14B?▶

Yes. At Q4 it generates ~24.6-29.7 tok/s and fits up to 138k context; beyond that it spills to SSD swap and slows to ~0.8-1 tok/s.

How much context fits?▶

At Q4, up to about 138k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.