Rent a GPU

Can the Apple M2 Pro (32GB) run Qwen3 Coder 30B-A3B?

Apple M2 Pro (32GB) × Qwen3 Coder 30B-A3B8K context
YesRuns fully on the GPU
Memory at Q4_K_M19.9 GB of 21.4 GB
Weights 18.5 GBKV cache 0.8 GBRuntime 0.6 GB
QuantQ4_K_MGood, most popular
Speed~60tokens per second
Max context22Ktokens that fit at Q4_K_M
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The Apple M2 Pro (32GB) can run Qwen3 Coder 30B-A3B fully in unified memory at Q4_K_M (good, most popular), using about 19.9 GB of the 21.4 GB available, at roughly 60 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 Coder 30B-A3B:

ollama run qwen3-coder:30b

Ollama's default download is Q4_K_M (about 19.9 GB here). That is also the best quant that fits.

New to this? Step-by-step setup for the Apple M2 Pro (32GB)

Run it in the cloud

No Apple M2 Pro (32GB)? Run Qwen3 Coder 30B-A3B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality62.4 GBToo big—
Q8_0Near-lossless33.8 GBToo big—
Q6_KExcellent26.4 GBToo big—
Q5_K_MVery good23.1 GBToo big—
Q4_K_MGood, most popular19.9 GBFits~60 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~74 tok/s
Q2_KHeavily degraded12.8 GBFits~97 tok/s

Measured speed from real Apple M2 Pro (32GB) owners

Tokens per second that people measured on their own Apple M2 Pro (32GB), next to our estimate.

No one has measured Qwen3 Coder 30B-A3B on the Apple M2 Pro (32GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Pro (32GB)? Add your real speed

One command times Qwen3 Coder 30B-A3B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- qwen3-coder:30b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3-coder:30b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3 Coder 30B-A3B comfortably

Models that run well on the Apple M2 Pro (32GB)

Frequently asked questions

Can Apple M2 Pro (32GB) run Qwen3 Coder 30B-A3B?

Yes. The Apple M2 Pro (32GB) can run Qwen3 Coder 30B-A3B fully in unified memory at Q4_K_M (good, most popular), using about 19.9 GB of the 21.4 GB available, at roughly 60 tokens/second.

How much VRAM does Qwen3 Coder 30B-A3B need?

About 19.9 GB at Q4_K_M with 8,192 tokens of context, and about 62.4 GB at full FP16 precision.

How fast is Qwen3 Coder 30B-A3B on the Apple M2 Pro (32GB)?

Roughly 60 tokens per second at Q4_K_M, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.