// RUN — FITS

Can the Apple M3 Max 36GB run Qwen3-1.7B?

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

Qwen3-1.7B on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 420k 60-72.4 t/s ~2-2.4 (slow)
Q8 yes 446k 120-144.7 t/s ~4-4.8 (slow)
Q4 yes 457k 214.3-258.4 t/s ~7.1-8.6 (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 → Qwen3-1.7B specs → Other hardware

FAQ

Can the Apple M3 Max 36GB run Qwen3-1.7B?▶

Yes. At Q4 it generates ~214.3-258.4 tok/s and fits up to 457k context; beyond that it spills to SSD swap and slows to ~7.1-8.6 tok/s.

How much context fits?▶

At Q4, up to about 457k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.