docs: cover Ollama setup, the composer memory chip, model details, and storage in the Cline Desktop local models guide

docs/usage/cline-desktop-local-models.mdx

@@ -1,17 +1,10 @@
 ---
 title: "Local Models in Cline Desktop"
 sidebarTitle: "Local Models"
-description: "Download, load, and switch between local Ollama models from Cline Desktop's settings, with recommendations based on your hardware."
+description: "Set up Ollama, download, load, and switch between local models, check their memory use, and manage disk space from Cline Desktop."
 ---
 
-The **Local Models** page in Cline Desktop's settings runs models on your own computer through [Ollama](https://ollama.com). It checks your hardware, recommends models that work well with Cline, and downloads, loads, and unloads them for you. When you pick a model, Cline sets up the Ollama provider and switches your chat to it.
-
-## Before you start
-
-1. Download and install Ollama from [ollama.com/download](https://ollama.com/download).
-2. Start Ollama. On macOS and Windows, open the Ollama app. On Linux, run `ollama serve`.
-
-Cline connects to Ollama at `http://localhost:11434` by default. If your Ollama server runs somewhere else, change the **Base URL** under **Settings → Providers → Ollama**.
+The **Local Models** page in Cline Desktop's settings runs models on your own computer through [Ollama](https://ollama.com). It helps you install and start Ollama, checks your hardware, recommends models that work well with Cline, and downloads, loads, and unloads them for you. When you pick a model, Cline sets up the Ollama provider and switches your chat to it.
 
 ## Open the Local Models page
 
@@ -27,9 +20,36 @@ Click **Settings** at the bottom of the sidebar, then select **Local Models**.
 The page shows:
 
 - **Your machine**: your processor, memory, and GPU, plus how large a model can run fully on the GPU.
-- **Ollama status**: whether Cline can reach Ollama, and which version is running. Click the refresh icon to check again.
+- **Ollama status**: whether Ollama is installed and running, and which version. If it isn't ready, the page walks you through setting it up.
+- **Loaded in memory**: models that are using memory right now, and how much.
 - **Recommended models**: models picked for agentic coding with Cline, each labeled with how well it fits your machine. The best fit gets a **Recommended for you** badge.
-- **Other downloaded models**: anything else you've downloaded with Ollama.
+- **Downloaded models**: every model on your disk, how much space each takes, and how much space is left.
+
+## Set up Ollama
+
+You don't need to set up Ollama before opening the page. It tells you what's missing.
+
+If Ollama isn't installed, the page shows how to install it on your system: a download button on macOS and Windows, or the install command on Linux.
+
+<Frame>
+  <img
+    src="/assets/local-models/desktop-ollama-not-installed.png"
+    alt="Ollama isn't installed, with steps to install Ollama, open it, and come back"
+  />
+</Frame>
+
+Once Ollama is installed, the page notices on its own within a few seconds. You don't need to restart Cline.
+
+If Ollama is installed but not running, click **Start Ollama**. Cline launches it in the background, and it keeps running after you close Cline.
+
+<Frame>
+  <img
+    src="/assets/local-models/desktop-ollama-not-running.png"
+    alt="Ollama is installed but not running, with a Start Ollama button"
+  />
+</Frame>
+
+Cline connects to Ollama at `http://localhost:11434` by default. If your Ollama server runs somewhere else, change the **Base URL** under **Settings → Providers → Ollama**. Cline can only start Ollama on your own computer, so for a remote server the page asks you to check that the server is running.
 
 ## Download a model
 
@@ -37,6 +57,8 @@ Click **Download** on a model. A progress bar shows how much has downloaded.
 
 The download keeps going if you leave settings or start a session. Reopen the Local Models page to see its progress again. Click **Cancel** to stop it.
 
+If a model is bigger than the free space on your disk, its **Download** button is turned off and the page shows how much space is free.
+
 ## Use a model with Cline
 
 Click **Use with Cline** on a downloaded model. Cline will:
@@ -45,46 +67,85 @@ Click **Use with Cline** on a downloaded model. Cline will:
 2. Save the model's recommended context window to the Ollama provider settings.
 3. Load the model into memory, so your first message doesn't wait for it to load.
 
-The model then shows an **In use** badge.
+The model then shows an **In use** badge. You can switch back to another provider or model from the pickers below the message box at any time.
+
+## Check memory use from the chat
+
+When the chat uses an Ollama model, a memory chip appears next to the **Thinking** picker below the message box. It shows how much memory the model is using, or **Not loaded** if it isn't in memory. The dot is green when the model is loaded and red when Cline can't reach Ollama.
+
+Click the chip to see more and act on it:
+
+- **Unload and free memory** when you're done with the model.
+- **Load now** to load the model before you send a message.
+- **Start Ollama** if Ollama isn't running.
+- Unload any other models that are using memory.
+- **Local model settings** opens the Local Models page.
 
 <Frame>
   <img
-    src="/assets/local-models/desktop-local-models-in-use.png"
-    alt="The recommended model with Use with Cline, Load, and Delete buttons, and a downloaded model marked In use and loaded"
+    src="/assets/local-models/desktop-composer-local-model.png"
+    alt="The memory chip below the message box, open to show qwen3:0.6b loaded and using 4.4 GB of 16.8 GB, with Unload and free memory and Local model settings buttons"
   />
 </Frame>
 
-Back in the chat, the provider and model pickers below the message box show the model:
-
-<Frame>
-  <img
-    src="/assets/local-models/desktop-composer-ollama.png"
-    alt="Cline Desktop chat input with the Ollama provider and qwen3:0.6b model selected"
-  />
-</Frame>
-
-You can switch back to another provider or model from these pickers at any time.
-
 ## Load and unload models
 
 A model has to be loaded into memory before it can respond. Click **Load** to load it ahead of time, and **Unload** to free up the memory when you're done.
 
-While a model is loaded, a green status line shows:
+Loaded models are listed under **Loaded in memory** at the top of the page, with how much of your computer's memory they're using.
+
+<Frame>
+  <img
+    src="/assets/local-models/desktop-loaded-in-memory.png"
+    alt="Loaded in memory section showing qwen3:0.6b in use, with a memory bar, 4.4 GB of 16.8 GB memory, and an Unload button"
+  />
+</Frame>
+
+Each loaded model shows:
 
 - Where it's running: fully on the GPU, on the CPU, or split between them. A model split between GPU and CPU responds more slowly.
 - How much memory it's using.
 - The context window it was loaded with.
 - How long it stays loaded.
 
-Models you load from this page stay in memory until you unload them. If Ollama loads a model on its own, for example when you send a message to a model that wasn't loaded, it unloads that model after a few minutes without requests. You can change that timeout with Ollama's `OLLAMA_KEEP_ALIVE` environment variable.
+Models you load from Cline stay in memory until you unload them. If Ollama loads a model on its own, for example when you send a message to a model that wasn't loaded, it unloads that model after a few minutes without requests. You can change that timeout with Ollama's `OLLAMA_KEEP_ALIVE` environment variable.
 
 <Tip>
 Local models use a lot of memory. Unload a model when you finish working with it to free that memory for other apps.
 </Tip>
 
-## Delete a model
+## View a model's settings
 
-Click the trash icon on a downloaded model to delete it from disk. You can download it again at any time.
+Click **Details** on a downloaded model to see how Ollama runs it. The settings are read-only for now.
+
+<Frame>
+  <img
+    src="/assets/local-models/desktop-model-details.png"
+    alt="Details for qwen3:0.6b showing its architecture, parameters, quantization, capabilities, the context window and keep-alive Cline uses, and sampling settings"
+  />
+</Frame>
+
+The details include:
+
+- **Model**: architecture, parameter count, quantization, size on disk, the longest context it supports, and what it can do, such as tool use, thinking, or vision.
+- **How Cline runs it**: the context window Cline requests, how long the model stays loaded, whether thinking is used, and how long Cline waits for a response to start.
+- **Sampling**: temperature, top P, top K, and the other settings that shape responses. Each one says whether the model sets it or Ollama's default applies.
+- **Advanced**: the model's prompt template, system prompt, Modelfile, and license.
+
+To change a model's settings, build your own version of it from a [Modelfile](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) with `ollama create`. It then appears under **Downloaded models**.
+
+## Free up disk space
+
+**Downloaded models** lists every model on your disk, largest first. A bar shows how much of your disk the models take, how much other files take, and how much is free.
+
+<Frame>
+  <img
+    src="/assets/local-models/desktop-downloaded-models.png"
+    alt="Downloaded models section with a storage bar showing models 104.2 GB, other files 22.7 GB, and 144.8 GB free, and a list of models with Details and Delete buttons"
+  />
+</Frame>
+
+Click **Delete** on a model, then confirm, to remove it from your disk. The confirmation shows how much space you'll get back. If the model is loaded, Cline unloads it first. You can download it again at any time.
 
 ## Which models are recommended
 
@@ -100,16 +161,19 @@ See [Recommended models](/running-models-locally/local-models-page#recommended-m
 
 ## Troubleshooting
 
-**"Ollama isn't running"**
-- Start the Ollama app, or run `ollama serve` in a terminal.
+**"Ollama isn't installed" after installing it**
+- Make sure the installer finished, then wait a few seconds or click the refresh icon.
+- Cline looks for Ollama on your `PATH` and in the usual install locations. If you installed it somewhere else, start it yourself with `ollama serve`.
+
+**"Start Ollama" doesn't start it**
+- Open the Ollama app yourself, or run `ollama serve` in a terminal, and watch for errors.
 - If Ollama runs on another machine or port, check the **Base URL** under **Settings → Providers → Ollama**.
-- Click the refresh icon next to the status to check again.
 
 **A model fails to load**
 - An out-of-memory error means the model and its context window don't fit. Unload other models, close memory-heavy apps, or pick a smaller model.
 
 **Responses are slow or time out**
-- Check the loaded status line. If the model runs partly or fully on the CPU, a smaller model will respond much faster.
+- Check where the model is loaded. If it runs partly or fully on the CPU, a smaller model will respond much faster.
 - On CPU-only machines, the first message of a session can take minutes while the model reads Cline's instructions. Later messages in the same session are faster.
 
 ## Related

docs/usage/cline-desktop.mdx

@@ -213,7 +213,7 @@ Cline Desktop can run sessions on a dev box, build server, or cloud VM while the
 
 ### 7. Run models on your own computer
 
-Open **Settings → Local Models** to run Cline with a model on your own hardware through Ollama. Cline recommends models that fit your machine, downloads them, and switches your chat to the one you pick. See [Local Models in Cline Desktop](/usage/cline-desktop-local-models).
+Open **Settings → Local Models** to run Cline with a model on your own hardware through Ollama. Cline helps you install and start Ollama, recommends models that fit your machine, downloads them, and switches your chat to the one you pick. A chip below the message box shows how much memory the model is using. See [Local Models in Cline Desktop](/usage/cline-desktop-local-models).
 
 ## Related