Rent a GPU

Can the Apple M3 Max (64GB) run Qwen3.6 35B-A3B?

Apple M3 Max (64GB) × Qwen3.6 35B-A3B8K context
YesRuns fully on the GPU
Memory at Q8_039 GB of 48 GB
Weights 38.3 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~75tokens per second
Max context256Kthe model's full window
  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 M3 Max (64GB) can run Qwen3.6 35B-A3B fully in unified memory at Q8_0 (near-lossless), using about 39 GB of the 48 GB available, at roughly 75 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3.6 35B-A3B:

ollama run qwen3.6:35b

Ollama's default download is Q4_K_M (about 22.6 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M3 Max (64GB)

Run it in the cloud

No Apple M3 Max (64GB)? Run Qwen3.6 35B-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 48 GB the Apple M3 Max (64GB) can use. macOS lets the GPU use about 48 GB of the 64 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality72.8 GBToo big—
Q8_0Near-lossless39 GBFits~75 tok/s
Q6_KExcellent30.3 GBFits~98 tok/s
Q5_K_MVery good26.4 GBFits~112 tok/s
Q4_K_MGood, most popular22.6 GBFits~132 tok/s
Q3_K_MNoticeably degraded18.4 GBFits~164 tok/s
Q2_KHeavily degraded14.3 GBFits~213 tok/s

Measured speed from real Apple M3 Max (64GB) owners

Tokens per second that people measured on their own Apple M3 Max (64GB), next to our estimate.

No one has measured Qwen3.6 35B-A3B on the Apple M3 Max (64GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M3 Max (64GB)? 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

Models that run well on the Apple M3 Max (64GB)

Frequently asked questions

Can Apple M3 Max (64GB) run Qwen3.6 35B-A3B?

Yes. The Apple M3 Max (64GB) can run Qwen3.6 35B-A3B fully in unified memory at Q8_0 (near-lossless), using about 39 GB of the 48 GB available, at roughly 75 tokens/second.

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 M3 Max (64GB)?

Roughly 75 tokens per second at Q8_0, estimated from the Apple M3 Max (64GB)'s 400 GB/s memory bandwidth.