AP Apple Consumer Unified memory

Apple M2 Max 32GB

Runs downloadable LLMs up to ~43.5B at Q4, ~60.7-73.2 tok/s on an 8B model.

Other configs: 64GB · 96GB
Apple M2 Max 32GB
32GB
Unified memory
400
GB/s bandwidth
43.5B
Max model (Q4)
$2,200
MSRP

What you can run

At 8k context, FP16 KV. Full-speed tok/s holds up to "max ctx"; beyond it the context spills to SSD swap and drops to the degraded figure.

Model sizeFP16Q8Q4
3B 45.3-54.7 t/s
≤325k ctx · then ~1.1-1.4 (slow)
90.7-109.3 t/s
≤371k ctx · then ~2.3-2.7 (slow)
161.9-195.2 t/s
≤391k ctx · then ~4-4.9 (slow)
7-8B 17-20.5 t/s
≤86k ctx · then ~0.4-0.5 (slow)
34-41 t/s
≤147k ctx · then ~0.9-1 (slow)
60.7-73.2 t/s
≤174k ctx · then ~1.5-1.8 (slow)
13B 10.5-12.6 t/s
≤8k ctx · then ~0.3-0.3 (slow)
20.9-25.2 t/s
≤87k ctx · then ~0.5-0.6 (slow)
37.4-45.1 t/s
≤122k ctx · then ~0.9-1.1 (slow)
32B won't run won't run 15.2-18.3 t/s
≤36k ctx · then ~0.4-0.5 (slow)
70B won't run won't run won't run
120B won't run won't run won't run
400B won't run won't run won't run

Estimate: tok/s ≈ bandwidth ÷ (params × bytes/param) × efficiency (Apple). Cyan = fits ~28.8 GB usable. Beyond "ctx", KV spills to SSD swap (rough degraded speed shown).

Run popular models on the Apple M2 Max 32GB

Videos about the Apple M2 Max 32GB

M2 Max MacBook Pro Review: Back to Bumps!

Apple Mac Studio M2 Max / M2 Ultra - A Long Term User Review

More hardware like the Apple M2 Max 32GB

About the Apple M2 Max 32GB

Apple M2 Max 32GB is a unified-memory system from Apple on Apple M2, 2023. For local genAI the numbers that matter are its 32 GB (how big a model + context fits) and 400 GB/s bandwidth (generation speed).

Frequently asked questions

What size LLM can the Apple M2 Max 32GB run?â–¶

With ~28.8 GB usable it runs up to ~43.5B at Q4 (~12.5B at FP16) at 8k context. Bigger spills into SSD swap and slows sharply.

How many tokens/sec does the Apple M2 Max 32GB generate?â–¶

Generation is bandwidth-bound. At 400 GB/s an 8B model at Q4 runs ~60.7-73.2 tok/s (estimate).

Why does long context slow it down?â–¶

The KV cache for the context must also fit fast memory; once weights+KV exceed 28.8 GB it spills to SSD swap and throughput collapses. Each row shows the max usable context.