feat(snippet): update llama.cpp snippet to include windows (#1476)

mfuntowicz · pcuenca · web-flow · commit b51d3f43207d · 2025-05-22T13:53:03.000+02:00
This PR adds the Windows way of installing and running llama.cpp on such
OSes.

llama.cpp is now available on WinGet and as easy installable as brew on
Windows machines now.


```powershelll
PS C:\Users\momo-&gt; winget install llama.cpp
PS C:\Users\momo-&gt; # Load and run the model:
PS C:\Users\momo-&gt; llama-cli -hf lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M
load_backend: loaded RPC backend from C:\Users\momo-\AppData\Local\Microsoft\WinGet\Packages\ggml.llamacpp_Microsoft.Winget.Source_8wekyb3d8bbwe\ggml-rpc.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce RTX 3090 (NVIDIA) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: KHR_coopmat
[...]
== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to the AI.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.
 - Not using system message. To change it, set a different value via -sys PROMPT


&gt; Hey how are you?
I'm just a language model, I don't have feelings or emotions like humans do, but I'm functioning properly and ready to help with any questions or tasks you may have! How about you? How's your day going?
```

---------

Co-authored-by: Pedro Cuenca &lt;pedro@huggingface.co&gt;
diff --git a/packages/tasks/src/local-apps.ts b/packages/tasks/src/local-apps.ts
@@ -121,6 +121,11 @@ const snippetLlamacpp = (model: ModelData, filepath?: string): LocalAppSnippet[]
 			setup: "brew install llama.cpp",
 			content: command("llama-cli"),
 		},
+		{
+			title: "Install from WinGet (Windows)",
+			setup: "winget install llama.cpp",
+			content: command("llama-cli"),
+		},
 		{
 			title: "Use pre-built binary",
 			setup: [
