New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Apple M1 Max 64GB
Runs downloadable LLMs up to ~95B at Q4, ~60.7-73.2 tok/s on an 8B model.
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 size | FP16 | Q8 | Q4 |
|---|---|---|---|
| 3B |
45.3-54.7 t/s ≤764k ctx · then ~1.1-1.4 (slow) |
90.7-109.3 t/s ≤810k ctx · then ~2.3-2.7 (slow) |
161.9-195.2 t/s ≤830k ctx · then ~4-4.9 (slow) |
| 7-8B |
17-20.5 t/s ≤306k ctx · then ~0.4-0.5 (slow) |
34-41 t/s ≤367k ctx · then ~0.9-1 (slow) |
60.7-73.2 t/s ≤394k ctx · then ~1.5-1.8 (slow) |
| 13B |
10.5-12.6 t/s ≤184k ctx · then ~0.3-0.3 (slow) |
20.9-25.2 t/s ≤263k ctx · then ~0.5-0.6 (slow) |
37.4-45.1 t/s ≤298k ctx · then ~0.9-1.1 (slow) |
| 32B | won't run |
8.5-10.3 t/s ≤92k ctx · then ~0.2-0.3 (slow) |
15.2-18.3 t/s ≤146k ctx · then ~0.4-0.5 (slow) |
| 70B | won't run | won't run |
6.9-8.4 t/s ≤52k ctx · then ~0.2-0.2 (slow) |
| 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 ~57.6 GB usable. Beyond "ctx", KV spills to SSD swap (rough degraded speed shown).
Run popular models on the Apple M1 Max 64GB
Videos about the Apple M1 Max 64GB
Gemma 4 on MacBook Pro M1 Max is INSANE! (Local LLM)
M1 Max MacBook Pro Review: Truly Next Level!
More hardware like the Apple M1 Max 64GB
About the Apple M1 Max 64GB
Apple M1 Max 64GB is a unified-memory system from Apple on Apple M1, 2021. For local genAI the numbers that matter are its 64 GB (how big a model + context fits) and 400 GB/s bandwidth (generation speed).
Frequently asked questions
What size LLM can the Apple M1 Max 64GB run?▶
With ~57.6 GB usable it runs up to ~95B at Q4 (~26.5B at FP16) at 8k context. Bigger spills into SSD swap and slows sharply.
How many tokens/sec does the Apple M1 Max 64GB generate?▶
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?▶
The KV cache for the context must also fit fast memory; once weights+KV exceed 57.6 GB it spills to SSD swap and throughput collapses. Each row shows the max usable context.