# Next Steps

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/)
- [Understand Mixture of Experts architecture for edge deployment](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/1_mixture_of_experts/)
- [Set up llama.cpp on an Armv9 development board](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/2_llamacpp_installation/)
- [Compare ERNIE model behavior and expert routing](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/3_ernie_moe/)
- [Optimize performance with Armv9 hardware features](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/4_v9_optimization/)
- [Next Steps](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/_next-steps/)

## Explore related resources

Find more information about the topics in this Learning Path:

- [ERNIE-4.5-21B Modelscope](https://modelscope.cn/models/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF)
- [llama.cpp GitHub repository](https://github.com/ggml-org/llama.cpp)
- [Build and run llama.cpp with Arm CPU optimizations](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/)

## Review frequently asked questions

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

### What result should I expect when verifying the setup on the Armv9 board?
You should see successful model inference and multilingual output from the ERNIE-4.5 Thinking variant. This confirms the `llama.cpp` build and runtime environment are working end to end.

### Which ERNIE-4.5 variant should I use for the comparison step?
Use both PT and Thinking on the same task and with the same settings. This makes the differences in response style and reasoning easier to observe.

### How do I inspect and interpret MoE expert routing during generation?
Use the inspection method shown in the steps to view which experts are selected per token. Compare activation patterns between PT and Thinking to understand routing differences.

### How do I set up baseline and optimized builds to benchmark Armv9 features?
Build a regular CPU version and a separate Armv9-specific version with SVE, i8mm, and dotprod enabled. Run the same benchmarks on both builds and compare results under identical conditions.

### What should I check if a model download or inference run fails?
Verify the device uses an Armv9 CPU and that at least 32 GB of disk space is available. Re-run the setup verification on the board before proceeding to comparisons or benchmarking.
