fix: clarify requirements (#22971)

Clarify supported platforms.

---------

Co-authored-by: Allie Sadler <[email protected]>

Author: ArthurFlag

_vale/Docker/Forbidden.yml

@@ -0,0 +1,6 @@
+extends: substitution
+message: "Use '%s' instead of '%s'."
+level: error
+ignorecase: false
+swap:
+  Docker CE: Docker Engine

_vale/config/vocabularies/Docker/accept.txt

@@ -1,7 +1,8 @@
 (?i)[A-Z]{2,}'?s
+Adreno
+Aleksandrov
 Amazon
 Anchore
-Aleksandrov
 Apple
 Artifactory
 Azure
@@ -114,6 +115,7 @@ Nginx
 npm
 Nutanix
 Nuxeo
+NVIDIA
 OAuth
 Okta
 Ollama
@@ -126,8 +128,7 @@ PKG
 Postgres
 PowerShell
 Python
-Pyright
-pyright
+Qualcomm
 rollback
 rootful
 runc
@@ -200,6 +201,7 @@ Zsh
 [Pp]rocfs
 [Pp]roxied
 [Pp]roxying
+[pP]yright
 [Rr]eal-time
 [Rr]egex(es)?
 [Rr]untimes?

content/manuals/ai/model-runner/_index.md

@@ -40,6 +40,41 @@ with AI models locally.
 - Run and interact with AI models directly from the command line or from the Docker Desktop GUI
 - Manage local models and display logs
 
+## Requirements 
+
+Docker Model Runner is supported on the following platforms:
+
+{{< tabs >}}
+{{< tab name="Windows">}}
+
+Windows(amd64):
+-  NVIDIA GPUs 
+-  NVIDIA drivers 576.57+
+
+Windows(arm64):
+- OpenCL for Adreno
+- Qualcomm Adreno GPU (6xx series and later)
+    
+  > [!NOTE]
+  > Some llama.cpp features might not be fully supported on the 6xx series.
+
+{{< /tab >}}
+{{< tab name="MacOS">}}
+
+- Apple Silicon
+
+{{< /tab >}}
+{{< tab name="Linux">}}
+
+Docker Engine only:
+
+- Linux CPU & Linux NVIDIA
+- NVIDIA drivers 575.57.08+
+
+{{< /tab >}}
+{{</tabs >}}
+
+
 ## How it works
 
 Models are pulled from Docker Hub the first time they're used and stored locally. They're loaded into memory only at runtime when a request is made, and unloaded when not in use to optimize resources. Since models can be large, the initial pull may take some time — but after that, they're cached locally for faster access. You can interact with the model using [OpenAI-compatible APIs](#what-api-endpoints-are-available).

data/summary.yaml

@@ -162,7 +162,7 @@ Docker Init:
 Docker Model Runner:
   availability: Beta
   requires: Docker Engine or Docker Desktop (Windows) 4.41+ or Docker Desktop (MacOS) 4.40+
-  for: Docker Desktop for Mac with Apple Silicon or Windows with NVIDIA GPUs
+  for: See Requirements section below
 Docker Projects:
   availability: Beta
 Docker Scout exceptions:

hugo_stats.json

@@ -84,6 +84,7 @@
       "Mac-and-Linux",
       "Mac-with-Apple-silicon",
       "Mac-with-Intel-chip",
+      "MacOS",
       "Manually-create-assets",
       "NetworkManager",
       "Networking-mode",
@@ -110,7 +111,9 @@
       "Run-Ollama-in-a-container",
       "Run-Ollama-outside-of-a-container",
       "Rust",
+      "Separate-containers",
       "Shell-script",
+      "Single-container",
       "Specific-version",
       "Svelte",
       "Ubuntu",