Skip to content

Stable Diffusion 3.5 Large on RTX 3090: VRAM, speed and fit

Stable Diffusion 3.5 Large at 16-bit runs on the RTX 3090, about 1.8 min per image.

Image generation · 1024 × 1024

Runs comfortably · on RTX 3090 · 16-bit (BF16)

GPU memory
16.1 GB
of 24.0 GB
Time
1.8 min
per image

Where the memory goes

Model
15.2 GB
Working
171 MB
Overhead
819 MB
OS
0.0 GB
Free
7.9 GB
Memory
16.1 GB of 24.0 GB
Output
1024 × 1024 · 28 steps
Time
1.8 min per image
Running cost
$8.65/mo at home · $30/mo on a cloud RTX A4500

Validation: Validated with conditions

What Stable Diffusion 3.5 Large on RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory24.0 GB usable16.1 GB neededPass
Headroom5% free7.9 GB free (33%)Pass
Time per imageunder 30 s1.8 minCheck

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 3090
GPU can use
24.0 GB of 24.0 GB

Running cost

At home
$8.65/mo
395 W at the wall, $0.002 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 22, 2026.

Where to get it

Stable Diffusion 3.5 Large on similar machines

  • RTX 4080 SuperRuns
  • RTX 5070 TiRuns
  • RTX 5080Runs
  • Radeon RX 7900 XTXRuns
  • RTX 4090Runs
  • Radeon AI PRO R9700Runs
  • RTX 5090Runs

All machines: Stable Diffusion 3.5 Large VRAM requirements. Everything that runs here: what can the RTX 3090 run?

Other models that run on RTX 3090

Questions

Can Stable Diffusion 3.5 Large run on RTX 3090?

Stable Diffusion 3.5 Large at 16-bit runs on the RTX 3090, about 1.8 min per image.

Report VR-10LHFC5, calculated Nov 22, 2026 from published specs, not benchmarked.