Rent a GPU

Can the Apple M2 Pro (32GB) run Qwen3.6 35B-A3B?

Apple M2 Pro (32GB) × Qwen3.6 35B-A3B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M18.4 GB of 21.4 GB
Weights 17.6 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~82tokens per second
Max context154Ktokens that fit at Q3_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

Only just. Qwen3.6 35B-A3B fits on the Apple M2 Pro (32GB) at Q3_K_M, which costs noticeable quality. Expect about 82 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwen3.6:35b download is Q4_K_M, which needs about 22.6 GB, more than the 21.4 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

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

Run it in the cloud

Want full quality? Run Qwen3.6 35B-A3B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 quality72.8 GBToo big—
Q8_0Near-lossless39 GBToo big—
Q6_KExcellent30.3 GBToo big—
Q5_K_MVery good26.4 GBToo big—
Q4_K_MGood, most popular22.6 GBToo big—
Q3_K_MNoticeably degraded18.4 GBFits~82 tok/s
Q2_KHeavily degraded14.3 GBFits~107 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 Qwen3.6 35B-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 Qwen3.6 35B-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 -- qwen3.6:35b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3.6:35b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3.6 35B-A3B comfortably

Check RTX 3090 prices

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

Frequently asked questions

Can Apple M2 Pro (32GB) run Qwen3.6 35B-A3B?

Only just. Qwen3.6 35B-A3B fits on the Apple M2 Pro (32GB) at Q3_K_M, which costs noticeable quality. Expect about 82 tokens/second. A card with more memory is a better experience.

How much VRAM does Qwen3.6 35B-A3B need?

About 22.6 GB at Q4_K_M with 8,192 tokens of context, and about 72.8 GB at full FP16 precision.

How fast is Qwen3.6 35B-A3B on the Apple M2 Pro (32GB)?

Roughly 82 tokens per second at Q3_K_M, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.