Rent a GPU

Can the Apple M3 Ultra (256GB) run Qwen3 235B-A22B?

Apple M3 Ultra (256GB) × Qwen3 235B-A22B8K context
YesRuns fully on the GPU
Memory at Q5_K_M169.4 GB of 192 GB
Weights 167.2 GBKV cache 1.6 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~31tokens per second
Max context32Kthe 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 Ultra (256GB) can run Qwen3 235B-A22B fully in unified memory at Q5_K_M (very good), using about 169.4 GB of the 192 GB available, at roughly 31 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 235B-A22B:

ollama run qwen3:235b

Ollama's default download is Q4_K_M (about 144.7 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M3 Ultra (256GB)

Run it in the cloud

No Apple M3 Ultra (256GB)? Run Qwen3 235B-A22B 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 192 GB the Apple M3 Ultra (256GB) can use. macOS lets the GPU use about 192 GB of the 256 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality472.4 GBToo big—
Q8_0Near-lossless252 GBToo big—
Q6_KExcellent195 GBToo big—
Q5_K_MVery good169.4 GBFits~31 tok/s
Q4_K_MGood, most popular144.7 GBFits~37 tok/s
Q3_K_MNoticeably degraded117.1 GBFits~46 tok/s
Q2_KHeavily degraded90.3 GBFits~60 tok/s

Measured speed from real Apple M3 Ultra (256GB) owners

Tokens per second that people measured on their own Apple M3 Ultra (256GB), next to our estimate.

No one has measured Qwen3 235B-A22B on the Apple M3 Ultra (256GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M3 Ultra (256GB)? Add your real speed

One command times Qwen3 235B-A22B 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 -- qwen3:235b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3:235b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

Models that run well on the Apple M3 Ultra (256GB)

Frequently asked questions

Can Apple M3 Ultra (256GB) run Qwen3 235B-A22B?

Yes. The Apple M3 Ultra (256GB) can run Qwen3 235B-A22B fully in unified memory at Q5_K_M (very good), using about 169.4 GB of the 192 GB available, at roughly 31 tokens/second.

How much VRAM does Qwen3 235B-A22B need?

About 144.7 GB at Q4_K_M with 8,192 tokens of context, and about 472.4 GB at full FP16 precision.

How fast is Qwen3 235B-A22B on the Apple M3 Ultra (256GB)?

Roughly 31 tokens per second at Q5_K_M, estimated from the Apple M3 Ultra (256GB)'s 819 GB/s memory bandwidth.