Rent a GPU

Can the Apple M4 Max (128GB) run Qwen3 Coder Next 80B-A3B?

Apple M4 Max (128GB) × Qwen3 Coder Next 80B-A3B8K context
YesRuns fully on the GPU
Memory at Q8_085.5 GB of 96 GB
Weights 84.7 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~103tokens 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 M4 Max (128GB) can run Qwen3 Coder Next 80B-A3B fully in unified memory at Q8_0 (near-lossless), using about 85.5 GB of the 96 GB available, at roughly 103 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 Coder Next 80B-A3B:

ollama run qwen3-coder-next

Ollama's default download is Q4_K_M (about 49.1 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 M4 Max (128GB)

Run it in the cloud

No Apple M4 Max (128GB)? Run Qwen3 Coder Next 80B-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 96 GB the Apple M4 Max (128GB) can use. macOS lets the GPU use about 96 GB of the 128 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality160.2 GBToo big—
Q8_0Near-lossless85.5 GBFits~103 tok/s
Q6_KExcellent66.2 GBFits~133 tok/s
Q5_K_MVery good57.5 GBFits~154 tok/s
Q4_K_MGood, most popular49.1 GBFits~180 tok/s
Q3_K_MNoticeably degraded39.8 GBFits~223 tok/s
Q2_KHeavily degraded30.7 GBFits~291 tok/s

Measured speed from real Apple M4 Max (128GB) owners

Tokens per second that people measured on their own Apple M4 Max (128GB), next to our estimate.

No one has measured Qwen3 Coder Next 80B-A3B on the Apple M4 Max (128GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M4 Max (128GB)? Add your real speed

One command times Qwen3 Coder Next 80B-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-next

Windows (PowerShell)

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

How the benchmark works

GPUs that run Qwen3 Coder Next 80B-A3B comfortably

Models that run well on the Apple M4 Max (128GB)

Frequently asked questions

Can Apple M4 Max (128GB) run Qwen3 Coder Next 80B-A3B?

Yes. The Apple M4 Max (128GB) can run Qwen3 Coder Next 80B-A3B fully in unified memory at Q8_0 (near-lossless), using about 85.5 GB of the 96 GB available, at roughly 103 tokens/second.

How much VRAM does Qwen3 Coder Next 80B-A3B need?

About 49.1 GB at Q4_K_M with 8,192 tokens of context, and about 160.2 GB at full FP16 precision.

How fast is Qwen3 Coder Next 80B-A3B on the Apple M4 Max (128GB)?

Roughly 103 tokens per second at Q8_0, estimated from the Apple M4 Max (128GB)'s 546 GB/s memory bandwidth.