Rent a GPU

Can the Apple M4 Pro (24GB) run QwQ 32B?

Apple M4 Pro (24GB) × QwQ 32B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K15 GB of 16.1 GB
Weights 12.3 GBKV cache 2.1 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~13tokens per second
Max context11Ktokens that fit at Q2_K
  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. QwQ 32B fits on the Apple M4 Pro (24GB) at Q2_K, which costs noticeable quality. Expect about 13 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwq:32b download is Q4_K_M, which needs about 22.6 GB, more than the 16.1 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the Apple M4 Pro (24GB)

Run it in the cloud

Want full quality? Run QwQ 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 16.1 GB the Apple M4 Pro (24GB) can use. macOS lets the GPU use about 16.1 GB of the 24 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 GBToo big—
Q2_KHeavily degraded15 GBFits~13 tok/s

Measured speed from real Apple M4 Pro (24GB) owners

Tokens per second that people measured on their own Apple M4 Pro (24GB), next to our estimate.

No one has measured QwQ 32B on the Apple M4 Pro (24GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M4 Pro (24GB)? Add your real speed

One command times QwQ 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 -- qwq:32b

Windows (PowerShell)

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

How the benchmark works

GPUs that run QwQ 32B comfortably

Check RTX 3090 prices

Models that run well on the Apple M4 Pro (24GB)

Frequently asked questions

Can Apple M4 Pro (24GB) run QwQ 32B?

Only just. QwQ 32B fits on the Apple M4 Pro (24GB) at Q2_K, which costs noticeable quality. Expect about 13 tokens/second. A card with more memory is a better experience.

How much VRAM does QwQ 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 QwQ 32B on the Apple M4 Pro (24GB)?

Roughly 13 tokens per second at Q2_K, estimated from the Apple M4 Pro (24GB)'s 273 GB/s memory bandwidth.