Qwen-Image on Mac mini M4 32 GB: VRAM, speed and fit
Qwen-Image at 16-bit needs 49.6 GB; the M4 32 GB can use 21.3 GB. The smallest machine we checked that runs it is the RTX PRO 5000 Blackwell 48 GB.
Image generation
Won’t fit · on M4 32 GB · 16-bit (BF16)
- GPU memory
- 60.2 GB
- of 32.0 GB
- Time
- n/a
Where the memory goes
- Model
- 45.8 GB
- Working
- 3.0 GB
- Overhead
- 819 MB
- OS
- 10.7 GB
- Over by
- 28.2 GB
- Memory
- 60.2 GB of 32.0 GB
- Output
- n/a
- Time
- Doesn’t run here
- Running cost
- Doesn’t run here · $72/mo on a cloud A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 21.3 GB usable | 49.6 GB needed | Fails |
| Headroom | 5% free | none | Fails |
| Time per image | under 30 s | – | Not run |
Targets: an image in under 30 s, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- Qwen-Image
- Parameters
- 20.4B
- Precision
- 16-bit (BF16)
- Hardware
- M4 32 GB
- GPU can use
- 21.3 GB of 32.0 GB
Worth trying
- RTX PRO 5000 Blackwell 48 GB: Runs it, 2.2 min an image
- M5 Ultra · 96 GB: Runs it, 6.6 min an image
- Ryzen AI Max+ 395 · 96 GB: Runs it, 17 min an image
Running cost
- At home
- n/a
- Doesn’t run on this machine.
- Renting instead
- $72/mo
- A40 at $0.59/h, $0.04 an image
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.
Where to get it
Qwen-Image on similar machines
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 Pro 24 GBToo big
- Mac mini M4 Pro 48 GBRuns
- Mac mini M4 Pro 64 GBRuns
- M4 Max 128 GBRuns
All machines: Qwen-Image VRAM requirements. Everything that runs here: what can the Mac mini M4 32 GB run?
Other models that run on Mac mini M4 32 GB
Questions
Can Qwen-Image run on Mac mini M4 32 GB?
Qwen-Image at 16-bit needs 49.6 GB; the M4 32 GB can use 21.3 GB. The smallest machine we checked that runs it is the RTX PRO 5000 Blackwell 48 GB.
Shown at the closest setup. Report VR-0ZTL752, calculated Nov 22, 2026 from published specs, not benchmarked.