Is it expected to work under Parallels Desktop?

[tleyden]

I'm tried running ollama under Parallels Desktop with an M2 OSX host and OSX guest OS, but I got this error:

ollama run llama3:latest
Error: llama runner process has terminated: signal: abort trap error:unsupported op 'MUL_MAT'
GGML_ASSERT: /Users/runner/work/ollama/ollama/llm/llama.cpp/ggml-metal.m:918: !"unsupported op"

I'm assuming that Parallels Desktop doesn't contain the proper hardware passthroughs? Just wondering if anyone knows a quick workaround.