Rent a GPU

Can the Apple M2 Ultra (192GB) run Qwen3 Coder 30B-A3B?

Apple M2 Ultra (192GB) × Qwen3 Coder 30B-A3B8K context
YesRuns fully on the GPU
Memory at FP1662.4 GB of 144 GB
Weights 61 GBKV cache 0.8 GBRuntime 0.6 GB
QuantFP16Full quality
Memory62.4 GBof 144 GB usable
Speed~73tokens per second
  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 Ultra (192GB) can run Qwen3 Coder 30B-A3B fully in unified memory at FP16 (full quality), using about 62.4 GB of the 144 GB available, at roughly 73 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). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M2 Ultra (192GB)

Run it in the cloud

No Apple M2 Ultra (192GB)? 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 144 GB the Apple M2 Ultra (192GB) can use. macOS lets the GPU use about 144 GB of the 192 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality62.4 GBFits~73 tok/s
Q8_0Near-lossless33.8 GBFits~137 tok/s
Q6_KExcellent26.4 GBFits~177 tok/s
Q5_K_MVery good23.1 GBFits~205 tok/s
Q4_K_MGood, most popular19.9 GBFits~240 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~298 tok/s
Q2_KHeavily degraded12.8 GBFits~388 tok/s

GPUs that run Qwen3 Coder 30B-A3B comfortably

Models that run well on the Apple M2 Ultra (192GB)

Frequently asked questions

Can Apple M2 Ultra (192GB) run Qwen3 Coder 30B-A3B?

Yes. The Apple M2 Ultra (192GB) can run Qwen3 Coder 30B-A3B fully in unified memory at FP16 (full quality), using about 62.4 GB of the 144 GB available, at roughly 73 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 Ultra (192GB)?

Roughly 73 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.