# Can I run Qwen3 32B on Apple M5 Pro (48GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~22 GB of ~32 GB usable.

Last validated: 2026-06-15.

## Memory math
- Qwen3 32B: 32B; Q4_K_M weighs 19.8 GB on disk.
- At Q4_K_M with a 4k context it needs ~22 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Apple M5 Pro (48GB): 48 GB unified, ~32 GB usable for model weights.
- Headroom: ~10 GB.

## How to run
Recommended quant: Q4_K_M. Best tool on macOS: LM Studio.

```sh
ollama run qwen3:32b
```

## Run Qwen3 32B on other devices
- [Nvidia GeForce RTX 4090 (24GB)](https://localmodel.run/can-i-run/qwen3-32b/nvidia-rtx-4090-24gb)
- [Nvidia GeForce RTX 3090 (24GB)](https://localmodel.run/can-i-run/qwen3-32b/nvidia-rtx-3090-24gb)
- [AMD Radeon RX 7900 XTX (24GB)](https://localmodel.run/can-i-run/qwen3-32b/amd-rx-7900-xtx-24gb)
- [Nvidia GeForce RTX 5090 (32GB)](https://localmodel.run/can-i-run/qwen3-32b/nvidia-rtx-5090-32gb)
- [32GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/qwen3-32b/laptop-32gb)
- [Apple M4 Pro (48GB)](https://localmodel.run/can-i-run/qwen3-32b/apple-m4-pro-48gb)

## Other models that run on Apple M5 Pro (48GB)
- [Mixtral 8x7B (46.7B)](https://localmodel.run/can-i-run/mixtral-8x7b/apple-m5-pro-48gb)
- [Command R 35B (35B)](https://localmodel.run/can-i-run/command-r-35b/apple-m5-pro-48gb)
- [Yi 1.5 34B (34B)](https://localmodel.run/can-i-run/yi-1.5-34b/apple-m5-pro-48gb)
- [Qwen2.5 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-32b/apple-m5-pro-48gb)
- [DeepSeek-R1-Distill-Qwen 32B (32B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-32b/apple-m5-pro-48gb)
- [Qwen2.5 Coder 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-coder-32b/apple-m5-pro-48gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/qwen3/tags, https://huggingface.co/Qwen/Qwen3-32B-GGUF, https://qwenlm.github.io/blog/qwen3/, https://lmarena.ai/leaderboard.
More: https://localmodel.run/can-i-run/qwen3-32b/apple-m5-pro-48gb