I ran your issue through ChatGPT and here's the response...
With the
v6 built-in AI in
Blue Iris, seeing
two identical entries for your NVIDIA GeForce RTX 3060 is expected behavior and comes down to how Blue Iris exposes GPU acceleration internally.
What’s actually happening
In v6, Blue Iris uses newer Windows AI/GPU APIs, and your RTX 3060 is exposed through
multiple execution providers, typically:
- DirectML (DML) → Microsoft’s universal GPU AI layer
- CUDA (sometimes indirectly exposed) → NVIDIA’s native compute path
Even though these are different backends, Blue Iris
doesn’t label them separately, so you end up seeing:
- NVIDIA GeForce RTX 3060
- NVIDIA GeForce RTX 3060
Same hardware, different AI pipelines.
Why this is more noticeable in v6
Earlier setups (with CodeProject.AI or DeepStack) made backend differences clearer.
In v6 built-in AI:
- Blue Iris handles inference internally
- It queries Windows ML / DirectX layers
- Multiple adapters/interfaces get listed as separate “GPUs”
Which one should you pick?
Unfortunately, since they’re unlabeled, the only reliable way is a quick test:
Quick test method
- Select the first RTX 3060 entry
- Trigger AI detections (walk in front of a camera, etc.)
- Open Task Manager → Performance → GPU
Look at:
- “Compute” or “CUDA” usage spikes → best option
- Minimal GPU usage + higher CPU → not ideal
Then repeat with the second entry.
What you’ll usually find
- One option will:
- Use more GPU
- Use less CPU
- Process alerts faster
That’s the one you keep.
Bottom line
- You do not have two GPUs
- This is normal for Blue Iris v6
- It’s just two different ways to use the same RTX 3060