// RUN — FITS

Can the Apple M3 Max 36GB run Qwen-VL?

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

Qwen-VL on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 89k 10.6-12.8 t/s ~0.4-0.4 (slow)
Q8 yes 163k 21.3-25.6 t/s ~0.7-0.9 (slow)
Q4 yes 195k 37.9-45.8 t/s ~1.3-1.5 (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 36GB → Qwen-VL specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run Qwen-VL?▶

Yes. At Q4 it generates ~37.9-45.8 tok/s and fits up to 195k context; beyond that it spills to SSD swap and slows to ~1.3-1.5 tok/s.

How much context fits?▶

At Q4, up to about 195k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.