Hi, I’m the Toradex AI Assistant.
I might make mistakes or occasionally get you wrong. Our support team will step in if needed.
This is a common Docker platform architecture issue when cross-compiling for ARM64 targets. The error indicates that the torizonextras/ide-port-tunnel:0.0.0 image was built only for AMD64 architecture but you’re trying to use it in an ARM64 build context (1).
Solution Steps
1. Enable ARM Emulation
First, ensure ARM emulation is properly configured on your development host (1):
docker run --rm -it --privileged torizon/binfmt
(1)
2. Explicitly Specify Platform
When building containers for ARM64, you need to explicitly specify the platform (2). You can do this in two ways:
Option A: Command Line
docker build --platform linux/arm64 .
(2)
Option B: In Dockerfile
FROM --platform=linux/arm64 torizon/debian:4
(2)
3. Clear Docker Cache
Remove any cached AMD64 versions of the problematic image:
docker image rm torizonextras/ide-port-tunnel:0.0.0
docker system prune -f
4. Verify Multi-Architecture Support
The torizonextras/ide-port-tunnel image may not have ARM64 support. You can check available architectures by pulling with explicit platform specification (3):
docker pull --platform=linux/arm64 torizonextras/ide-port-tunnel:0.0.0
Platform Architecture Guidelines
When cross-compiling on a development host for Toradex modules, always specify the target platform (2):
- For ARM64 modules (iMX8, AM62, AM69, iMX95): Use
--platform linux/arm64
- For ARM32 modules (iMX6/7): Use
--platform linux/arm/v7
The Torizon containers are built for specific architectures, and when pulling images on a development host, Docker’s automatic architecture selection may not match your target (3).
IDE Extension Considerations
If you’re using the Torizon IDE Extension, check your project configuration to ensure the target architecture is correctly set to ARM64. The extension should handle platform specification automatically, but configuration resets can cause it to default back to AMD64.
Best regards, Toradex AI Assistant.
Did you like my answer?

If I answered your question, please tick the “Solution” checkbox.
For follow-up questions to me, please use @ToradexAI in your post.