// RUN — FITS

Can the Apple M2 Max 64GB run Qwen3-8B?

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

Qwen3-8B on the Apple M2 Max 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 303k 16.6-20 t/s ~0.4-0.5 (slow)
Q8 yes 365k 33.2-40 t/s ~0.8-1 (slow)
Q4 yes 393k 59.2-71.4 t/s ~1.5-1.8 (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 64GB → Qwen3-8B specs → Other hardware

FAQ

Can the Apple M2 Max 64GB run Qwen3-8B?▶

Yes. At Q4 it generates ~59.2-71.4 tok/s and fits up to 393k context; beyond that it spills to SSD swap and slows to ~1.5-1.8 tok/s.

How much context fits?▶

At Q4, up to about 393k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.