Can an Apple M3 Max 36GB run Qwen3 30B A3B?

In practice

On paper the Apple M3 Max 36GB has 36 GB, and Qwen3 30B A3B at Q8_0 needs 31.27 GB. macOS does not let the GPU use all of it: by default about 70% is available, which is 25.2 GB. So the model is just over the default limit and well inside the physical memory.

The limit is a setting, and one command raises it for the current session. It resets at reboot, and the memory it takes comes from the rest of the system, so keep other large programs closed while the model is loaded. Once it is raised the estimate is about 39.2 tokens per second.

The numbers

Qwen3 30B A3B has 30.53 billion parameters across 48 layers, of which 3.34 billion are read for each token. The Apple M3 Max 36GB has 36 GB of unified memory at 400 GB/s, of which about 25.2 GB is left for a model once the operating system has taken its share.

8 of the 9 levels fit entirely. Levels marked degraded are listed for completeness, not as advice.

The settings we would use

sudo sysctl iogpu.wired_limit_mb=33792

macOS lets the GPU wire down about 70% of the memory by default, which is less than this model needs. The command raises the limit for this session and resets at reboot.

Once the limit is raised, Ollama and LM Studio use the extra memory without further settings. Run ollama ps and check that the processor column reads 100% GPU, and see the Mac and PC comparison for what unified memory does well and where it is slow.

If you would rather not change the limit

A smaller model from the same family is the straightforward answer. These fit on an Apple M3 Max 36GB at a quantization worth using:

• Qwen3 14B, 14.77B at Q8_0, 16.28 GB, about 18.0 tokens/s
• Qwen2.5 14B Instruct, 14.77B at Q8_0, 16.53 GB, about 17.7 tokens/s
• Qwen2.5 Coder 14B Instruct, 14.77B at Q8_0, 16.53 GB, about 17.7 tokens/s

What else an Apple M3 Max 36GB runs well

For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.

The same model on nearby hardware

Memory decides whether Qwen3 30B A3B loads and bandwidth decides how quickly it answers. Here is what a step down, a card with the same memory and a step up do with it.

Wait for the first word803 ms

Then writes at39.2 tok/s

Whole answer5.2 s

YouWhy does my model use more memory when the conversation gets longer?

Model

Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.

Questions people ask

Keep going

Everything the Apple M3 Max 36GB runs, the full breakdown for Qwen3 30B A3B, how the numbers are made in the methodology, or a different pairing in the calculator.