Qwen-Image on RTX 5080: VRAM, speed and fit
Qwen-Image at 5-bit runs on the RTX 5080, about 5.9 min per image.
Image generation · 1328 × 1328
Runs comfortably · on RTX 5080 · 5-bit (GGUF Q5_K_M)
- GPU memory
- 14.7 GB
- of 16.0 GB
- Time
- 5.9 min
- per image
Where the memory goes
- Model
- 13.6 GB
- Working
- 347 MB
- Overhead
- 819 MB
- OS
- 0.0 GB
- Free
- 1.3 GB
- Memory
- 14.7 GB of 16.0 GB
- Output
- 1328 × 1328 · 50 steps
- Time
- 5.9 min per image
- Running cost
- $8.84/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 | 14.7 GB needed | Pass |
| Headroom | 5% free | 1.3 GB free (8%) | Pass |
| Time per image | under 30 s | 5.9 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
- Parameters
- 20.4B
- Precision
- 5-bit (GGUF Q5_K_M)
- Output
- 1328 × 1328
- Steps
- 50
- Hardware
- RTX 5080
- GPU can use
- 16.0 GB of 16.0 GB
Running cost
- At home
- $8.84/mo
- 404 W at the wall, $0.007 an image
- Renting instead
- $29/mo
- RTX 2000 Ada at $0.24/h, $0.05 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 on similar machines
- Radeon RX 9070 XTRuns
- RTX 4070 Ti SuperRuns
- RTX 4080 SuperRuns
- RTX 5070 TiRuns
- Radeon RX 7900 XTXRuns
- RTX 3090Runs
- RTX 4090Runs
- Radeon AI PRO R9700Runs
All machines: Qwen-Image VRAM requirements. Everything that runs here: what can the RTX 5080 run?
Other models that run on RTX 5080
Questions
Can Qwen-Image run on RTX 5080?
Qwen-Image at 5-bit runs on the RTX 5080, about 5.9 min per image.
Report VR-0WS2CRA, calculated Nov 22, 2026 from published specs, not benchmarked.