Windows ARM64 fails when loading model, error code 0xc000001d

### What is the issue? I installed the latest Ollama for Windows (ARM64 build) on my 2023 Windows Dev Kit, which has an 8-core ARM processor, a Snapdragon 8cx Gen 3. It's running Windows 11 Pro. I can pull models, but when I go to run them, I get an error. It doesn't matter what model I run, I've tried several. Here's an example. ``` C:\Users\Mike Chambers>ollama pull gemma2:2b pulling manifest pulling 7462734796d6... 100% ▕████████████████████████████████████████████████████████▏ 1.6 GB pulling e0a42594d802... 100% ▕████████████████████████████████████████████████████████▏ 358 B pulling 097a36493f71... 100% ▕████████████████████████████████████████████████████████▏ 8.4 KB pulling 2490e7468436... 100% ▕████████████████████████████████████████████████████████▏ 65 B pulling e18ad7af7efb... 100% ▕████████████████████████████████████████████████████████▏ 487 B verifying sha256 digest writing manifest success C:\Users\Mike Chambers>ollama run gemma2:2b Error: llama runner process has terminated: exit status 0xc000001d C:\Users\Mike Chambers> ``` ### OS Windows ### GPU _No response_ ### CPU Other ### Ollama version 0.3.13 [server.log](https://github.com/user-attachments/files/17448637/server.log)