Skip to content

Stable Diffusion 3.5 Large on RTX 5090: VRAM, speed and fit

Stable Diffusion 3.5 Large at 16-bit runs on the RTX 5090, about 38 s per image.

Image generation · 1024 × 1024

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

GPU memory
16.1 GB
of 32.0 GB
Time
38 s
per image

Where the memory goes

Model
15.2 GB
Working
171 MB
Overhead
819 MB
OS
0.0 GB
Free
15.9 GB
Memory
16.1 GB of 32.0 GB
Output
1024 × 1024 · 28 steps
Time
38 s per image
Running cost
$13/mo at home · $30/mo on a cloud RTX A4500

Validation: Validated with conditions

What Stable Diffusion 3.5 Large on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable16.1 GB neededPass
Headroom5% free15.9 GB free (50%)Pass
Time per imageunder 30 s38 sCheck

Targets: an image in under 30 s, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Stable Diffusion 3.5 Large
Parameters
8.1B
Precision
16-bit (BF16)
Output
1024 × 1024
Steps
28
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$13/mo
598 W at the wall, $0.001 an image
Renting instead
$30/mo
RTX A4500 at $0.25/h, $0.006 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

Stable Diffusion 3.5 Large 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: Stable Diffusion 3.5 Large VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Stable Diffusion 3.5 Large run on RTX 5090?

Stable Diffusion 3.5 Large at 16-bit runs on the RTX 5090, about 38 s per image.

Report VR-0TH4Q8M, calculated Nov 22, 2026 from published specs, not benchmarked.