Rent a GPU

Can the Apple M2 Ultra (192GB) run Qwen2.5 32B?

Apple M2 Ultra (192GB) × Qwen2.5 32B8K context
YesRuns fully on the GPU
Memory at FP1668.3 GB of 144 GB
Weights 65.6 GBKV cache 2.1 GBRuntime 0.6 GB
QuantFP16Full quality
Memory68.3 GBof 144 GB usable
Speed~7tokens 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 Qwen2.5 32B fully in unified memory at FP16 (full quality), using about 68.3 GB of the 144 GB available, at roughly 7 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen2.5 32B:

ollama run qwen2.5:32b

Ollama's default download is Q4_K_M (about 22.6 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 Qwen2.5 32B 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 quality68.3 GBFits~7 tok/s
Q8_0Near-lossless37.6 GBFits~14 tok/s
Q6_KExcellent29.6 GBFits~18 tok/s
Q5_K_MVery good26.1 GBFits~21 tok/s
Q4_K_MGood, most popular22.6 GBFits~24 tok/s
Q3_K_MNoticeably degraded18.8 GBFits~30 tok/s
Q2_KHeavily degraded15 GBFits~39 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 Qwen2.5 32B 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 Qwen2.5 32B 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 -- qwen2.5:32b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen2.5:32b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen2.5 32B comfortably

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

Frequently asked questions

Can Apple M2 Ultra (192GB) run Qwen2.5 32B?

Yes. The Apple M2 Ultra (192GB) can run Qwen2.5 32B fully in unified memory at FP16 (full quality), using about 68.3 GB of the 144 GB available, at roughly 7 tokens/second.

How much VRAM does Qwen2.5 32B need?

About 22.6 GB at Q4_K_M with 8,192 tokens of context, and about 68.3 GB at full FP16 precision.

How fast is Qwen2.5 32B on the Apple M2 Ultra (192GB)?

Roughly 7 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.