Skip to content

Qwen-Image 2.1 on RTX 5090: VRAM, speed and fit

Qwen-Image 2.1 at 16-bit runs on the RTX 5090, about 72 s per image.

Image generation · 2048 × 2048

Runs comfortably · on RTX 5090 · 16-bit (BF16)

GPU memory
15.1 GB
of 32.0 GB
Time
72 s
per image

Where the memory goes

Model
13.3 GB
Working
1.0 GB
Overhead
819 MB
OS
0.0 GB
Free
16.9 GB
Memory
15.1 GB of 32.0 GB
Output
2048 × 2048 · 40 steps
Time
72 s per image
Running cost
$13/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated with conditions

What Qwen-Image 2.1 on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable15.1 GB neededPass
Headroom5% free16.9 GB free (53%)Pass
Time per imageunder 30 s72 sCheck

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
16-bit (BF16)
Output
2048 × 2048
Steps
40
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$13/mo
598 W at the wall, $0.002 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

  • Radeon RX 7900 XTXRuns
  • RTX 3090Runs
  • RTX 4090Runs
  • Radeon AI PRO R9700Runs
  • RTX PRO 5000 Blackwell 48 GBRuns
  • RTX 6000 AdaRuns

All machines: Qwen-Image 2.1 VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Qwen-Image 2.1 run on RTX 5090?

Qwen-Image 2.1 at 16-bit runs on the RTX 5090, about 72 s per image.

Report VR-1K06422, calculated Nov 22, 2026 from published specs, not benchmarked.