codinit-dev · Gerome-Elassaad · Dec 20, 2025 · Dec 20, 2025 · Dec 20, 2025 · Dec 20, 2025
diff --git a/docs.json b/docs.json
@@ -66,6 +66,14 @@
                   "features/development/webcontainer",
                   "features/development/workbench"
                 ]
+              },
+              {
+                "group": "AI Features",
+                "expanded": false,
+                "pages": [
+                  "essentials/ai-chat-commands",
+                  "essentials/project-templates"
+                ]
               }
             ]
           },
@@ -136,18 +144,14 @@
             "expanded": false,
             "pages": ["integrations/vercel", "integrations/netlify", "integrations/cloudflare"]
           },
-          {
-            "group": "Local Providers",
-            "expanded": false,
-            "pages": ["providers/lmstudio", "providers/ollama"]
-          },
           {
             "group": "Running Models Locally",
             "icon": "cpu",
             "expanded": false,
             "pages": [
-              "running-models-locally/lm-studio",
-              "running-models-locally/local-model-setup"
+              "running-models-locally/local-model-setup",
+              "providers/lmstudio",
+              "providers/ollama"
             ]
           }
         ]

diff --git a/providers/lmstudio.mdx b/providers/lmstudio.mdx
@@ -23,7 +23,7 @@

 ## How It Works

 LM Studio downloads and runs AI models locally using your computer's resources. It provides a simple interface to manage models, start local servers, and connect to various applications including Codinit.

 <AccordionGroup>
  <Accordion title="Model Management" icon="download">
@@ -63,14 +63,52 @@
 ## Setup Instructions
 
 <Steps>
-  <Step title="Download LM Studio">Visit [LM Studio website](https://lmstudio.ai/) and download the application</Step>
-  <Step title="Install and Launch">Install LM Studio and launch the application</Step>
-  <Step title="Download Models">Browse the model library and download models you want to use</Step>
-  <Step title="Start Local Server">Click "Start Server" in LM Studio to begin the local API server</Step>
-  <Step title="Configure in Codinit">Set the server URL (usually http://localhost:1234) in Codinit settings</Step>
-  <Step title="Test Connection">Verify the connection and start using local AI models</Step>
+  <Step title="Download LM Studio">
+    Visit [lmstudio.ai](https://lmstudio.ai) and download the application for your operating system.
+
+    ![LM Studio download page](/assets/images/lmstudio.webp)
+  </Step>
+  <Step title="Install and Launch">
+    Install LM Studio and launch the application. You'll see four tabs on the left:
+    - **Chat**: Interactive chat interface
+    - **Developer**: Where you will start the server
+    - **My Models**: Your downloaded models storage
+    - **Discover**: Browse and add new models
+  </Step>
+  <Step title="Download a Model">
+    Navigate to the "Discover" tab, browse available models, and download your preferred model. Wait for the download to complete.
+
+    **Recommended**: Use **Qwen3 Coder 30B A3B Instruct** for the best experience with CodinIT. This model delivers strong coding performance and reliable tool use.
+  </Step>
+  <Step title="Start the Server">
+    Navigate to the "Developer" tab and toggle the server switch to "Running". The server will run at `http://localhost:51732`.
+
+    ![Starting the LM Studio server](/assets/images/lmstudio.webp)
+  </Step>
+  <Step title="Configure Model Settings">
+    After loading your model in the Developer tab, configure these critical settings:
+    - **Context Length**: Set to 262,144 (the model's maximum)
+    - **KV Cache Quantization**: Leave unchecked (critical for consistent performance)
+    - **Flash Attention**: Enable if available (improves performance)
+  </Step>
+  <Step title="Configure in CodinIT">
+    Set the server URL in CodinIT settings and verify the connection to start using local AI models.
+  </Step>
 </Steps>
 
+### Quantization Guide
+
+Choose quantization based on your available RAM:
+
+- **32GB RAM**: Use 4-bit quantization (~17GB download)
+- **64GB RAM**: Use 8-bit quantization (~32GB download) for better quality
+- **128GB+ RAM**: Consider full precision or larger models
+
+### Model Format
+
+- **Mac (Apple Silicon)**: Use MLX format for optimized performance
+- **Windows/Linux**: Use GGUF format
+
 ## Key Features
 
 <BadgeGroup>
@@ -209,3 +247,19 @@
 <Callout type="warning">
   **Resource Intensive**: Large models require significant RAM and may run slowly on lower-end hardware.
 </Callout>
+
+## Troubleshooting
+
+If CodinIT can't connect to LM Studio:
+
+1. Verify LM Studio server is running (check Developer tab)
+2. Ensure a model is loaded
+3. Check your system meets hardware requirements
+4. Confirm the server URL matches in CodinIT settings
+
+## Important Notes
+
+- Start LM Studio before using with CodinIT
+- Keep LM Studio running in background
+- First model download may take several minutes depending on size
+- Models are stored locally after download
diff --git a/running-models-locally/lm-studio.mdx b/running-models-locally/lm-studio.mdx