Can an Apple M4 16GB run Qwen3 32B?
Yes, with a setting
It needs 14.08 GB at IQ3_XXS and macOS allows 10.72 GB by default. Raise the limit and it runs at about 6.1 tokens per second.
In practice
It loads, and we would not call that running it. The only quantization that fits the Apple M4 16GB is IQ3_XXS, which compresses the weights far enough that Qwen3 32B loses a visible amount of its ability, so we do not recommend it. At Q4_K_M it needs 20.83 GB against the 10.72 GB available.
A smaller model at a proper quantization is a better answer than a larger one squeezed in, and the next section lists the ones that fit.
The numbers
Qwen3 32B has 32.76 billion parameters across 64 layers. The Apple M4 16GB has 16 GB of unified memory at 120 GB/s, of which about 10.72 GB is left for a model once the operating system has taken its share.
| Quantization | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 34.83 GB | no | n/a |
| Q6_K | 27.43 GB | no | n/a |
| Q5_K_M | 24.11 GB | no | n/a |
| Q4_K_M | 20.83 GB | no | n/a |
| IQ4_XS | 18.62 GB | no | n/a |
| Q3_K_M | 17.32 GB | no | n/a |
| IQ3_XXS degraded | 14.08 GB | with raised limit | 6.1 t/s |
| Q2_K degraded | 15.19 GB | no | n/a |
| IQ2_XXS degraded | 10.27 GB | yes | 8.4 t/s |
1 of the 9 levels fit entirely. Levels marked degraded are listed for completeness, not as advice.
If you would rather not change the limit
A smaller model from the same family is the straightforward answer. These fit on an Apple M4 16GB at a quantization worth using:
- Qwen3 14B, 14.77B at IQ4_XS, 8.97 GB, about 10.0 tokens/s
- Qwen2.5 14B Instruct, 14.77B at Q3_K_M, 8.63 GB, about 10.4 tokens/s
- Qwen2.5 Coder 14B Instruct, 14.77B at Q3_K_M, 8.63 GB, about 10.4 tokens/s
Models of this size are what a second GPU or a large-memory machine is for. The multi-GPU guide shows what 2 cards add, and the Mac and PC comparison shows where unified memory holds a model that no single card can.
What else an Apple M4 16GB runs well
For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.
| Model | Quantization | Memory | Speed |
|---|---|---|---|
| Qwen3.5 9B | Q6_K | 8.04 GB | 11.8 t/s |
| Gemma 4 12B Instruct | Q4_K_M | 8.41 GB | 10.2 t/s |
| Qwen3 8B | Q6_K | 7.76 GB | 11.8 t/s |
| Qwen3 14B | IQ4_XS | 8.97 GB | 10.0 t/s |
The same model on nearby hardware
Memory decides whether Qwen3 32B 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.
| Device | Memory | Bandwidth | Result |
|---|---|---|---|
| GeForce RTX 4070 | 12 GB | 504 GB/s | does not fit |
| GeForce RTX 5080 | 16 GB | 960 GB/s | does not fit |
| GeForce RTX 4090 | 24 GB | 1008 GB/s | Q4_K_M, 37.1 t/s |
See how fast it feels
Apple M4 16GB running Qwen3 32B at IQ3_XXS
YouWhy does my model use more memory when the conversation gets longer?
Reading your question
Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.
Questions people ask
How much VRAM does Qwen3 32B need on Apple M4 16GB?
At Q4_K_M with an 8k context window it needs 20.83 GB in total: 18.42 GB of weights, 2 GB of KV cache and 0.41 GB of runtime overhead. The Apple M4 16GB makes about 10.72 GB available once the operating system has taken its share.
Can I run Qwen3 32B on Apple M4 16GB anyway?
Yes, after raising the macOS GPU memory limit, which one sysctl command does. Without it the model needs 14.08 GB and the default limit allows 10.72 GB.
Keep going
Everything the Apple M4 16GB runs, the full breakdown for Qwen3 32B, how the numbers are made in the methodology, or a different pairing in the calculator.