Can I Run Qwen3-Coder on Mac mini (M4 Pro, 64 GB)?
作者： Jakub Rusinowski · 最后更新： 2026年9月29日
Yes — comfortably
Yes, comfortably — Qwen3-Coder 30B-A3B (MoE) at Q8_0 needs about 34 GB of the 48 GB usable on Mac mini (M4 Pro, 64 GB), leaving ~14 GB spare and running at ~34.3 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~34.3 tok/s
See what else this hardware can run →
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
Mac mini (M4 Pro, 64 GB) — what it gives a model
| Usable memory for models | 48 GB |
| Memory bandwidth | 273 GB/s |
| Form factor | Mini PC |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
Qwen3-Coder on Mac mini (M4 Pro, 64 GB): memory by quantization
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 62.6 GB | ✗ No | — | — | 61 GB |
| Q8_0 | 34 GB | ✓ Yes | 128K | ~34.3 tok/s | 32.4 GB |
| Q6_K | 26.6 GB | ✓ Yes | 128K | ~42.1 tok/s | 25 GB |
| Q5_K_M | 23.2 GB | ✓ Yes | 128K | ~46.9 tok/s | 21.6 GB |
| Q4_K_M | 20 GB | ✓ Yes | 256K | ~52.6 tok/s | 18.4 GB |
| Q3_K_M | 14.6 GB | ✓ Yes | 256K | ~66.3 tok/s | 13 GB |
| Q2_K | 11.6 GB | ✓ Yes | 256K | ~77.3 tok/s | 10 GB |
Which Qwen3-Coder sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen3-Coder 480B-A35B (MoE) | 291.6 GB | ✗ Too large | — |
| Qwen3-Coder-Next (80B-A3B MoE) | 49.4 GB | ✗ Too large | — |
| Qwen3-Coder 30B-A3B (MoE) | 20 GB | ✓ Fits | ~52.6 tok/s |
What to watch out for
- 2 larger variants of Qwen3-Coder do not fit and would need CPU offload or different hardware.
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
Mac mini M4 Pro 64 GB limitations
- M4 Pro memory bandwidth is half the M4 Max's, so large models that fit will still generate roughly half as fast.
Recommended setup
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 64 GB unified memory at 273 GB/s, shared between CPU and GPU.
- macOS reserves a share of unified memory for the system, so not all of it is available to a model.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Qwen3-Coder on Mac mini (M4 Pro, 64 GB)?
Yes, comfortably — Qwen3-Coder 30B-A3B (MoE) at Q8_0 needs about 34 GB of the 48 GB usable on Mac mini (M4 Pro, 64 GB), leaving ~14 GB spare and running at ~34.3 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of Qwen3-Coder should I use on Mac mini (M4 Pro, 64 GB)?
Q8_0 — it needs about 34 GB of the 48 GB available, downloads as roughly 32.4 GB, and runs at an estimated 34.3 tokens/sec with up to 128K of context.
What limits Qwen3-Coder on Mac mini (M4 Pro, 64 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Other Computers
Other Models on Mac mini (M4 Pro, 64 GB)
- SmolLM2 on Mac mini (M4 Pro, 64 GB)
- SmolLM3 on Mac mini (M4 Pro, 64 GB)
- StarCoder 2 on Mac mini (M4 Pro, 64 GB)
- Aya 3B (Tiny Aya) on Mac mini (M4 Pro, 64 GB)
- VibeThinker on Mac mini (M4 Pro, 64 GB)
Qwen3-Coder on GPUs
- Qwen3-Coder on NVIDIA GeForce RTX 5070
- Qwen3-Coder on NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen3-Coder on NVIDIA GeForce RTX 5060
- Qwen3-Coder on NVIDIA GeForce RTX 4070 Ti
What This Model Is Good At
Model & Tools
← Can I Run It? | Qwen3-Coder model page | Check your hardware