Rent a GPU

Can the Apple M2 Ultra (192GB) run Qwen3 235B-A22B?

Apple M2 Ultra (192GB) × Qwen3 235B-A22B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M117.1 GB of 144 GB
Weights 114.9 GBKV cache 1.6 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~45tokens 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

Only just. Qwen3 235B-A22B fits on the Apple M2 Ultra (192GB) at Q3_K_M, which costs noticeable quality. Expect about 45 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwen3:235b download is Q4_K_M, which needs about 144.7 GB, more than the 144 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

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

Run it in the cloud

Want full quality? Run Qwen3 235B-A22B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 quality472.4 GBToo big—
Q8_0Near-lossless252 GBToo big—
Q6_KExcellent195 GBToo big—
Q5_K_MVery good169.4 GBToo big—
Q4_K_MGood, most popular144.7 GBToo big—
Q3_K_MNoticeably degraded117.1 GBFits~45 tok/s
Q2_KHeavily degraded90.3 GBFits~58 tok/s

Measured speed from real Apple M2 Ultra (192GB) owners

Tokens per second that people measured on their own Apple M2 Ultra (192GB), next to our estimate.

No one has measured Qwen3 235B-A22B on the Apple M2 Ultra (192GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Ultra (192GB)? 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

GPUs that run Qwen3 235B-A22B comfortably

Check Mac Studio M3 Ultra (256 GB) prices

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

Frequently asked questions

Can Apple M2 Ultra (192GB) run Qwen3 235B-A22B?

Only just. Qwen3 235B-A22B fits on the Apple M2 Ultra (192GB) at Q3_K_M, which costs noticeable quality. Expect about 45 tokens/second. A card with more memory is a better experience.

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 M2 Ultra (192GB)?

Roughly 45 tokens per second at Q3_K_M, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.