diff --git a/docs/src/pages/docs/desktop/linux.mdx b/docs/src/pages/docs/desktop/linux.mdx index d82ca4503..727b1e727 100644 --- a/docs/src/pages/docs/desktop/linux.mdx +++ b/docs/src/pages/docs/desktop/linux.mdx @@ -28,166 +28,147 @@ import FAQBox from '@/components/FaqBox' # Linux Installation To install Jan desktop on Linux, follow the steps below: ## Compatibility - Ensure that your system meets the following requirements to use Jan effectively: + + -- Debian-based (Supports `.deb` and `AppImage` ) - - Ubuntu-based - - Ubuntu Desktop LTS (official)/ Ubuntu Server LTS (only for server) - - Edubuntu (Mainly desktop) - - Kubuntu (Desktop only) - - Lubuntu (Both desktop and server, though mainly desktop) - - Ubuntu Budgie (Mainly desktop) - - Ubuntu Cinnamon (Desktop only) - - Ubuntu Kylin (Both desktop and server) - - Ubuntu MATE (Desktop only) -- Pacman-based - - Arch Linux based - - Arch Linux (Mainly desktop) - - SteamOS (Desktop only) -- RPM-based (Supports `.rpm` and `AppImage` ) -- Fedora-based - - RHEL-based (Server only) +#### Debian-based (Supports `.deb` and `AppImage`) +- Debian +- Ubuntu and derivatives: + - Ubuntu Desktop LTS (official)/Ubuntu Server LTS (only for server) + - Edubuntu (Mainly desktop) + - Kubuntu (Desktop only) + - Lubuntu (Both desktop and server, though mainly desktop) + - Ubuntu Budgie (Mainly desktop) + - Ubuntu Cinnamon (Desktop only) + - Ubuntu Kylin (Both desktop and server) + - Ubuntu MATE (Desktop only) + +#### RHEL-based (Supports `.rpm` and `AppImage`) +- RHEL-based (Server only) +- Fedora + +#### Arch-based +- Arch Linux (Mainly desktop) +- SteamOS (Desktop only) + +#### Independent - openSUSE (Both desktop and server) - - - Please check whether your Linux distribution supports desktop, server, or both environments. - - - - - - -- Jan supports a processor that can handle AVX2. For the full list, please see [here](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2). -- We support older processors with AVX and AVX-512, though this is not recommended. +Please check whether your Linux distribution supports desktop, server, or both environments. -- Haswell processors (Q2 2013) and newer. -- Tiger Lake (Q3 2020) and newer for Celeron and Pentium processors. + +- Haswell processors (Q2 2013) and newer +- Tiger Lake (Q3 2020) and newer for Celeron and Pentium processors +- Excavator processors (Q2 2015) and newer + -- Jan supports a processor that can handle AVX2. For the full list, please see [here](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2). -- We support older processors with AVX and AVX-512, though this is not recommended. +Jan requires a processor with AVX2 for best performance. See [full list of supported processors.](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2) While older processors with AVX/AVX-512 will work, you may experience slower performance. -- Excavator processors (Q2 2015) and newer. + + +- 8GB → 3B models (int4) +- 16GB → 7B models (int4) +- 32GB → 13B models (int4) + + +DDR2 RAM minimum supported, newer generations recommended for better performance. + + + + +- 6GB → 3B model (int4) with `ngl` at 120 +- 8GB → 7B model (int4) with `ngl` at 120 +- 12GB → 13B model (int4) with `ngl` at 120 + + +Minimum 6GB VRAM recommended for NVIDIA, AMD, or Intel Arc GPUs. + + + + +At least 10GB for app installation and model downloads. + + - - -- 8GB for running up to 3B models (int4). -- 16GB for running up to 7B models (int4). -- 32GB for running up to 13B models (int4). - -We support DDR2 RAM as the minimum requirement but recommend using newer generations of RAM for improved performance. - - - - -- 6GB can load the 3B model (int4) with `ngl` at 120 ~ full speed on CPU/ GPU. -- 8GB can load the 7B model (int4) with `ngl` at 120 ~ full speed on CPU/ GPU. -- 12GB can load the 13B model (int4) with `ngl` at 120 ~ full speed on CPU/ GPU. - - -Having at least 6GB VRAM when using NVIDIA, AMD, or Intel Arc GPUs is recommended. - - - - -- At least 10GB for app storage and model download. - - -## Prerequisites - -- **System Libraries**: - - glibc 2.27 or higher. You can verify this by running `ldd --version`. - - Install gcc-11, g++-11, cpp-11, or later versions. Refer to the [Ubuntu installation guide](https://gcc.gnu.org/projects/cxx-status.html#cxx17) for assistance. -- **Post-Installation Actions**: - - Add CUDA libraries to the `LD_LIBRARY_PATH` per the instructions in the [Post-installation Actions](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions). - -## Installing Jan +## Install Jan To install Jan, follow the steps below: -### Step 1: Download the Jan Application +### Step 1: Download Application -Jan provides two types of releases: - +Jan provides 3 types of releases: + -#### Stable Releases +Please download Jan from official distributions, or build it from source. + - Download Jan on **Ubuntu**: [jan.deb](https://app.jan.ai/download/latest/linux-amd64-deb) + - Download Jan on **Fedora**: [jan.AppImage](https://app.jan.ai/download/latest/linux-amd64-appimage) +- Official Website: https://jan.ai/download -The stable release is a stable version of Jan. You can download a stable release Jan app via the following: + + -- **Official Website**: [https://jan.ai](https://jan.ai/) -- **Jan GitHub repository**: [Github](https://github.com/janhq/jan/releases) +Beta releases let you test new features, which may be buggy: + - Download Jan's Beta Version on **Ubuntu**: [jan.deb](https://app.jan.ai/download/beta/linux-amd64-deb) + - Download Jan's Beta Version on **Fedora**: [jan.AppImage](https://app.jan.ai/download/beta/linux-amd64-appimage) -Make sure to verify the URL to ensure that it's the official Jan website and GitHub repository. +Keep in mind that this build might crash frequently or contain bugs! -#### Nightly Releases -The nightly Release allows you to test out new features and get a sneak peek at what might be included in future stable releases. You can download this version via: +Nightly releases are for internal team to test new feature builds everyday, which is very be buggy: -- **Jan GitHub repository**: [Github](https://github.com/janhq/jan/actions/workflows/jan-electron-build-nightly.yml) + - Download Jan's Nightly Version on **Ubuntu**: [jan.deb](https://app.jan.ai/download/nightly/linux-amd64-deb) + - Download Jan's Nightly Version on **Fedora**: [jan.AppImage](https://app.jan.ai/download/nightly/linux-amd64-appimage) -Keep in mind that this build might crash frequently and may contain bugs! +Keep in mind that this build crashes frequently or contains bugs! -For Linux, Jan provides two types of downloads: -1. **Ubuntu**: `.deb` -2. **Fedora**: `.AppImage` - -### Step 2: Install the Jan Application +### Step 2: Install Application Here are the steps to install Jan on Linux based on your Linux distribution: + -### Ubuntu -Install Jan using the following command: - - - -``` +Install Jan using either **dpkg** or **apt-get**: +##### dpkg +```bash # Install Jan using dpkg sudo dpkg -i jan-linux-amd64-{version}.deb - ``` - - -```json +##### apt-get +```bash # Install Jan using apt-get sudo apt-get install ./jan-linux-amd64-{version}.deb # where jan-linux-amd64-{version}.deb is the path to the Jan package ``` - - + -### Fedora - 1. Make the AppImage executable using the following command: - -``` - chmod +x jan-linux-x86_64-{version}.AppImage - +```bash +chmod +x jan-linux-x86_64-{version}.AppImage ``` 2. Run the AppImage file using the following command: - -``` - ./jan-linux-x86_64-{version}.AppImage - +```bash +./jan-linux-x86_64-{version}.AppImage ``` + ## Data Folder By default, Jan is installed in the following directory: @@ -202,65 +183,60 @@ or ~/.config/Jan/data ``` +See [Jan Data Folder](/docs/data-folder) for more details about the data folder structure. - -- Please see the [Jan Data Folder](/docs/data-folder) for more details about the data folder structure. - ## GPU Acceleration - Once Jan is installed and you have a GPU, you can use your GPU to accelerate the model's performance. -### NVIDIA GPU - -To enable the use of your NVIDIA GPU in the Jan app, follow the steps below: + + Ensure that you have installed the following to use NVIDIA GPU: -- NVIDIA GPU with CUDA Toolkit 11.7 or higher. -- NVIDIA driver 470.63.01 or higher. - +- **NVIDIA GPU** with CUDA Toolkit 11.7 or higher +- **NVIDIA driver** 470.63.01 or higher -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> **GPU Acceleration**. -3. Enable and choose the NVIDIA GPU you want. -4. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. +To enable the use of your NVIDIA GPU in the Jan app, follow the steps below: +1. Open Jan application +2. Go to **Settings** → **Advanced Settings** → **GPU Acceleration** +3. Enable and choose the NVIDIA GPU you want +4. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated While **Vulkan** can enable Nvidia GPU acceleration in the Jan app, **CUDA** is recommended for faster performance. - + -### AMD GPU - + To enable the use of your AMD GPU in the Jan app, you need to activate the Vulkan support first by following the steps below: -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> enable the **Experimental Mode**. -3. Enable the **Vulkan Support** under the **GPU Acceleration**. -4. Enable the **GPU Acceleration** and choose the GPU you want to use. -5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. - -### Intel Arc GPU +1. Open Jan application +2. Go to **Settings** → **Advanced Settings** → enable the **Experimental Mode** +3. Enable the **Vulkan Support** under the **GPU Acceleration** +4. Enable the **GPU Acceleration** and choose the AMD GPU you want to use +5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated + + To enable the use of your Intel Arc GPU in the Jan app, you need to activate the Vulkan support first by following the steps below: -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> enable the **Experimental Mode**. -3. Enable the **Vulkan Support** under the **GPU Acceleration**. -4. Enable the **GPU Acceleration** and choose the GPU you want to use. -5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. +1. Open Jan application +2. Go to **Settings** → **Advanced Settings** → enable the **Experimental Mode** +3. Enable the **Vulkan Support** under the **GPU Acceleration** +4. Enable the **GPU Acceleration** and choose the Intel Arc GPU you want to use +5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated + + -## Uninstalling Jan +## Uninstall Jan -To uninstall Jan, follow the steps below: +Open **Terminal** and run these commands to remove all Jan-related data: -### Ubuntu - ```bash # Uninstall Jan sudo apt-get remove jan @@ -276,7 +252,6 @@ rm -rf ~/.config/Jan/cache ``` -### Fedora ```bash # Uninstall Jan @@ -291,9 +266,8 @@ rm -rf ~/.config/Jan/cache - -The deleted Data Folder cannot be restored. - + +Deleted data folders cannot be restored. Make sure to backup any important data before proceeding with deletion. {/* ## FAQs diff --git a/docs/src/pages/docs/desktop/mac.mdx b/docs/src/pages/docs/desktop/mac.mdx index 456c775ec..849b45ce5 100644 --- a/docs/src/pages/docs/desktop/mac.mdx +++ b/docs/src/pages/docs/desktop/mac.mdx @@ -79,7 +79,7 @@ Keep in mind that this build might crash frequently or contain bugs! -Nightly releases are for internal team to test new feature build everyday, which is very be buggy: +Nightly releases are for internal team to test new feature builds everyday, which is very be buggy: [Download Jan's Nightly Version](https://app.jan.ai/download/nightly/mac-universal) @@ -133,7 +133,9 @@ rm -rf ~/Library/Application\ Support/Jan/data # Delete application cache rm -rf ~/Library/Application\ Support/Jan/cache ``` -This will completely remove Jan and all associated data from your system. + +Deleted data folders cannot be restored. Make sure to backup any important data before proceeding with deletion. + {/* ## FAQs diff --git a/docs/src/pages/docs/desktop/windows.mdx b/docs/src/pages/docs/desktop/windows.mdx index f22f8984b..53c0ee20e 100644 --- a/docs/src/pages/docs/desktop/windows.mdx +++ b/docs/src/pages/docs/desktop/windows.mdx @@ -40,8 +40,7 @@ Ensure that your system meets the following requirements to use Jan effectively: -- Jan requires a processor with AVX2 for best performance. See [full list of supported processors.](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2) -- While older processors with AVX/AVX-512 will work, you may experience slower performance. +Jan requires a processor with AVX2 for best performance. See [full list of supported processors.](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2) While older processors with AVX/AVX-512 will work, you may experience slower performance. - **Memory (RAM)** - 8GB → 3B parameter models (int4) @@ -51,11 +50,11 @@ Ensure that your system meets the following requirements to use Jan effectively: DDR2 RAM is supported but newer RAM generations are recommended for better performance. - **GPU**: - - 6GB → 3B models with number of GPU layers (`ngl`) at 120 (full speed) - - 8GB → 7B models with number of GPU layers (`ngl`) at 120 (full speed) - - 12GB → 13B models with number of GPU layers (`ngl`) at 120 (full speed) + - 6GB → 3B models with **ngl** at 120 (full speed) + - 8GB → 7B models with **ngl** at 120 (full speed) + - 12GB → 13B models with **ngl** at 120 (full speed) -Having at least 6GB VRAM when using NVIDIA, AMD, or Intel Arc GPUs is recommended. +Minimum 6GB VRAM recommended for NVIDIA, AMD, or Intel Arc GPUs. - **Storage:** Minimum 10GB free space for application and model downloads @@ -87,7 +86,7 @@ Keep in mind that this build might crash frequently or contain bugs! -Nightly releases are for internal team to test new feature build everyday, which is very be buggy: +Nightly releases are for internal team to test new feature builds everyday, which is very be buggy: [Download Jan's Nightly Version](https://app.jan.ai/download/nightly/win-x64) @@ -113,76 +112,79 @@ By default, Jan is installed in the following directory: ``` - -- Please see the [Jan Data Folder](/docs/data-folder) for more details about the data folder structure. - +See [Jan Data Folder](/docs/data-folder) for more details about the data folder structure. + ## GPU Acceleration +Jan can leverage your GPU to significantly improve model performance and inference speed. Here's how to enable GPU acceleration for different hardware: -Once Jan is installed and you have a GPU, you can use your GPU to accelerate the model's performance. + -### NVIDIA GPU - -To enable the use of your NVIDIA GPU in the Jan app, follow the steps below: + +Before enabling NVIDIA GPU support, ensure you have: +- **CUDA Toolkit** 11.7 or higher installed +- **NVIDIA driver** version 470.63.01 or higher +Follow the steps below to enable the use of your NVIDIA GPU: +1. Launch Jan +2. Navigate to **Settings** → **Advanced Settings** → Turn on **GPU Acceleration** +3. Select and enable your NVIDIA GPU +4. App reload is required after the selection -Ensure that you have installed the following to use NVIDIA GPU: -- NVIDIA GPU with CUDA Toolkit 11.7 or higher. -- NVIDIA driver 470.63.01 or higher. +While Jan supports both CUDA and Vulkan for NVIDIA GPUs, we strongly recommend using CUDA for optimal performance. + -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> **GPU Acceleration**. -3. Enable and choose the NVIDIA GPU you want. -4. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. + +AMD GPUs require **Vulkan** support, which must be activated through **Experimental Mode**. +1. Launch Jan +2. Navigate to **Settings** → **Advanced Settings** +3. Enable **Experimental Mode** +4. Under **GPU Acceleration**, enable **Vulkan Support** +5. Enable **GPU Acceleration** and select your AMD GPU +6. App reload is required after the selection + - -While **Vulkan** can enable Nvidia GPU acceleration in the Jan app, **CUDA** is recommended for faster performance. - + +Intel Arc GPUs require **Vulkan** support, which must be activated through **Experimental Mode**. +1. Launch Jan +2. Navigate to **Settings** → **Advanced Settings** +3. Enable **Experimental Mode** +4. Under **GPU Acceleration**, enable **Vulkan Support** +5. Enable **GPU Acceleration** and select your Intel Arc GPU +6. App reload is required after the selection + -### AMD GPU + -To enable the use of your AMD GPU in the Jan app, you need to activate the Vulkan support first by following the steps below: - -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> enable the **Experimental Mode**. -3. Enable the **Vulkan Support** under the **GPU Acceleration**. -4. Enable the **GPU Acceleration** and choose the AMD GPU you want to use. -5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. - -### Intel Arc GPU - -To enable the use of your Intel Arc GPU in the Jan app, you need to activate the Vulkan support first by following the steps below: - -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> enable the **Experimental Mode**. -3. Enable the **Vulkan Support** under the **GPU Acceleration**. -4. Enable the **GPU Acceleration** and choose the Intel Arc GPU you want to use. -5. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. ## Uninstall Jan -To uninstall Jan, follow the steps below: +### Step 1: Remove Application through Control Panel -### Step 1: Open the Control Panels +1. Open **Control Panels** +2. Go to **Programs** section +3. Click **Uninstall Program** +4. Search for **Jan** +5. Click the **three dots icon → Uninstall** +6. Click **Uninstall** again to confirm +7. Click **OK** -1. Open the **Control Panels**. -2. Click **Uninstall Program** under the **Programs** section. +### Step 2: Handle Jan Data +When prompted with: `Do you also want to delete the DEFAULT Jan data folder at C:\Users{username}\Jan?` +- Click **OK** to remove all Jan data +- Click **Cancel** to keep your Jan data for future installations -### Step 2: Uninstall Application +### Step 3: Clean Up Remaining Files -1. Search for **Jan**. -2. Click the **three dots icon** -> **Uninstall**. -3. Click **Uninstall** once again to confirm the action. -4. Click **OK**. -5. A message will appear: **"Do you also want to delete the DEFAULT Jan data folder at C:\Users\{username}\Jan?"**. -6. Click **OK** to delete the entire Jan data folder, or click **Cancel** to save your Jan Data folder so you can use this on the new installation folder. -7. Navigate to `users/{username}/AppData/Roaming`. -8. Delete the `Jan` folder that contains the app cache. +To ensure a complete uninstallation, remove the app cache: + +1. Navigate to `C:\Users\[username]\AppData\Roaming` +2. Delete Jan folder -The deleted Data Folder cannot be restored. +Deleted data folders cannot be restored. Make sure to backup any important data before proceeding with deletion. {/* ## FAQs diff --git a/docs/src/pages/docs/quickstart.mdx b/docs/src/pages/docs/quickstart.mdx index 89077df5d..535695d09 100644 --- a/docs/src/pages/docs/quickstart.mdx +++ b/docs/src/pages/docs/quickstart.mdx @@ -60,11 +60,10 @@ For more model installation methods, please visit [Model Management](/docs/model
### Step 3: Turn on the GPU Acceleration (Optional) -While waiting for model downloading, let's customize your hardware setup. If you have a graphics card, boost model performance by enabling GPU acceleration: -1. Open Jan application. -2. Go to **Settings** -> **Advanced Settings** -> **GPU Acceleration**. -3. Click the Slider and choose your preferred GPU. -3. A success notification saying **Successfully turned on GPU acceleration** will appear when GPU acceleration is activated. +While the model downloads, let's optimize your hardware setup. If you have a compatible graphics card, you can significantly boost model performance by enabling GPU acceleration:1. Open Jan application. +1. Navigate to **Settings** → **Advanced Settings** → Turn on **GPU Acceleration** +2. Choose your preferred GPU +3. App reload is required after the selection Ensure you have installed your GPU driver. Please see [Desktop](/docs/desktop) for more information on activating the GPU acceleration.