Rent a GPU

Can the Apple M2 Pro (32GB) run DeepSeek R1 Distill Qwen 32B?

Apple M2 Pro (32GB) × DeepSeek R1 Distill Qwen 32B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M18.8 GB of 21.4 GB
Weights 16 GBKV cache 2.1 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Memory18.8 GBof 21.4 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

Only just. DeepSeek R1 Distill Qwen 32B fits on the Apple M2 Pro (32GB) at Q3_K_M, which costs noticeable quality. Expect about 7 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default deepseek-r1:32b download is Q4_K_M, which needs about 22.6 GB, more than the 21.4 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 Pro (32GB)

Run it in the cloud

Want full quality? Run DeepSeek R1 Distill Qwen 32B 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 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality68.3 GBToo big—
Q8_0Near-lossless37.6 GBToo big—
Q6_KExcellent29.6 GBToo big—
Q5_K_MVery good26.1 GBToo big—
Q4_K_MGood, most popular22.6 GBToo big—
Q3_K_MNoticeably degraded18.8 GBFits~7 tok/s
Q2_KHeavily degraded15 GBFits~10 tok/s

Measured speed from real Apple M2 Pro (32GB) owners

Tokens per second that people measured on their own Apple M2 Pro (32GB), next to our estimate.

No one has measured DeepSeek R1 Distill Qwen 32B on the Apple M2 Pro (32GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Pro (32GB)? Add your real speed

One command times DeepSeek R1 Distill Qwen 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 -- deepseek-r1:32b

Windows (PowerShell)

$env:GPUFIT_MODEL="deepseek-r1:32b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run DeepSeek R1 Distill Qwen 32B comfortably

Check NVIDIA RTX 3090 prices

Models that run well on the Apple M2 Pro (32GB)

Frequently asked questions

Can Apple M2 Pro (32GB) run DeepSeek R1 Distill Qwen 32B?

Only just. DeepSeek R1 Distill Qwen 32B fits on the Apple M2 Pro (32GB) at Q3_K_M, which costs noticeable quality. Expect about 7 tokens/second. A card with more memory is a better experience.

How much VRAM does DeepSeek R1 Distill Qwen 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 DeepSeek R1 Distill Qwen 32B on the Apple M2 Pro (32GB)?

Roughly 7 tokens per second at Q3_K_M, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.