Qwen-Image 2.1 on Mac mini M4 24 GB: VRAM, speed and fit
Qwen-Image 2.1 at 4-bit runs on the M4 24 GB, about 74 min per image.
Image generation · 2048 × 2048
Tight fit · on M4 24 GB · 4-bit (GGUF Q4_K_M · NVFP4)
100% used
- GPU memory
- 23.9 GB
- of 24.0 GB
- Time
- 74 min
- per image
Where the memory goes
- Model
- 12.1 GB
- Working
- 3.0 GB
- Overhead
- 819 MB
- OS
- 8.0 GB
- Free
- 58 MB
- Memory
- 23.9 GB of 24.0 GB
- Output
- 2048 × 2048 · 40 steps
- Time
- 74 min per image
- Running cost
- $1.28/mo at home · $29/mo on a cloud RTX 2000 Ada
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 16.0 GB usable | 15.9 GB needed | Pass |
| Headroom | 5% free | 58 MB free (0%) | Check |
| Time per image | under 30 s | 74 min | Fails |
Targets: an image in under 30 s, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- Qwen-Image 2.1
- Parameters
- 7.1B
- Precision
- 4-bit (GGUF Q4_K_M · NVFP4)
- Output
- 2048 × 2048
- Steps
- 40
- Hardware
- M4 24 GB
- GPU can use
- 16.0 GB of 24.0 GB
Worth trying
- 1536² output: Fits, 36 min an image
- RTX PRO 2000 Blackwell: Runs it, 4.2 min an image
- M5 Max · 36 GB: Runs it, 5.4 min an image
- Ryzen AI Max+ 395 · 32 GB: Runs it, 8.2 min an image
Running cost
- At home
- $1.28/mo
- 59 W at the wall, $0.01 an image
- Renting instead
- $29/mo
- RTX 2000 Ada at $0.24/h, $0.02 an image
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.
Where to get it
Qwen-Image 2.1 on similar machines
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 32 GBRuns
- Mac mini M4 Pro 24 GBRuns
- Mac mini M4 Pro 48 GBRuns
- Mac mini M4 Pro 64 GBRuns
All machines: Qwen-Image 2.1 VRAM requirements. Everything that runs here: what can the Mac mini M4 24 GB run?
Other models that run on Mac mini M4 24 GB
Questions
Can Qwen-Image 2.1 run on Mac mini M4 24 GB?
Qwen-Image 2.1 at 4-bit runs on the M4 24 GB, about 74 min per image.
Report VR-0R4JSKX, calculated Nov 22, 2026 from published specs, not benchmarked.