updated installation pages

This commit is contained in:
Ashley 2025-01-07 14:27:52 +07:00
parent bd4d81842c
commit 31120d2d54
3 changed files with 79 additions and 55 deletions

View File

@ -23,6 +23,7 @@ keywords:
import FAQBox from '@/components/FaqBox'
import { Tabs, Callout, Steps } from 'nextra/components'
import { Settings } from 'lucide-react'
@ -68,14 +69,14 @@ Please check whether your Linux distribution supports desktop, server, or both e
- Excavator processors (Q2 2015) and newer
<Callout type="info">
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 or newer** for optimal performance. See [full list of supported processors](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2). While Jan may run on processors with only AVX support, performance will be significantly reduced.
</Callout>
</Tabs.Tab>
<Tabs.Tab>
- 8GB → 3B models (int4)
- 16GB → 7B models (int4)
- 32GB → 13B models (int4)
- 8GB → up to 3B parameter models (int4)
- 16GB → up to 7B parameter models (int4)
- 32GB → up to 13B parameter models (int4)
<Callout type="info">
DDR2 RAM minimum supported, newer generations recommended for better performance.
@ -83,9 +84,9 @@ DDR2 RAM minimum supported, newer generations recommended for better performance
</Tabs.Tab>
<Tabs.Tab>
- 6GB → 3B model (int4) with `ngl` at 120
- 8GB → 7B model (int4) with `ngl` at 120
- 12GB → 13B model (int4) with `ngl` at 120
- 6GB → up to 3B parameter models (int4)
- 8GB → up to 7B parameter models (int4)
- 12GB → up to 13B parameter models (int4)
<Callout type="info">
Minimum 6GB VRAM recommended for NVIDIA, AMD, or Intel Arc GPUs.
@ -93,7 +94,7 @@ Minimum 6GB VRAM recommended for NVIDIA, AMD, or Intel Arc GPUs.
</Tabs.Tab>
<Tabs.Tab>
At least 10GB for app installation and model downloads.
At least **10GB** for app installation and model downloads.
</Tabs.Tab>
</Tabs>
@ -179,7 +180,7 @@ chmod +x jan-linux-x86_64-{version}.AppImage
By default, Jan is installed in the following directory:
```
```bash
# Custom installation directory
$XDG_CONFIG_HOME = /home/username/custom_config
@ -238,9 +239,9 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64
See [detailed instructions](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions).
### Step 2: Enable GPU Acceleration
1. In Jan, navigate to **Settings** > **Hardware**
3. Select and enable your prefered NVIDIA GPU(s)
4. App reload is required after the selection
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
3. App reload is required after the selection
<Callout type="info">
@ -252,23 +253,32 @@ While **Vulkan** can enable Nvidia GPU acceleration in the Jan app, **CUDA** is
</Tabs.Tab>
<Tabs.Tab>
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:
AMD GPUs require **Vulkan** support.
<Callout type="warning">
This feature is currently experimental and must be enabled through [Experimental Mode](/docs/settings#experimental-mode) in **Advanced Settings**.
</Callout>
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. Enable **Experimental Mode**
3. Under **GPU Acceleration**, enable **Vulkan Support**
4. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
5. App reload is required after the selection
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
</Tabs.Tab>
<Tabs.Tab>
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:
Intel Arc GPUs require **Vulkan** support.
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
<Callout type="warning">
This feature is currently experimental and must be enabled through [Experimental Mode](/docs/settings#experimental-mode) in **Advanced Settings**.
</Callout>
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. Enable **Experimental Mode**
3. Under **GPU Acceleration**, enable **Vulkan Support**
4. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
5. App reload is required after the selection
</Tabs.Tab>
</Tabs>

View File

@ -132,14 +132,7 @@ See [Jan Data Folder](/docs/data-folder) for more details about the data folder
Open **Terminal** and run these commands to remove all Jan-related data:
```bash
# Remove all user data
rm -rf ~/jan
# Delete application data
rm -rf ~/Library/Application\ Support/Jan/data
# Delete application cache
rm -rf ~/Library/Application\ Support/Jan/cache
```
</Steps>

View File

@ -22,6 +22,7 @@ keywords:
import { Tabs, Callout, Steps } from 'nextra/components'
import FAQBox from '@/components/FaqBox'
import { Settings } from 'lucide-react'
# Windows Installation
@ -39,23 +40,29 @@ Ensure that your system meets the following requirements to use Jan effectively:
- Excavator processors (Q2 2015) and newer.
</Tabs.Tab>
</Tabs>
<Callout type="info">
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 or newer** for optimal performance. See [full list of supported processors](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#CPUs_with_AVX2). While Jan may run on processors with only AVX support, performance will be significantly reduced.
</Callout>
- **Memory (RAM)**
- 8GB > 3B parameter models (int4)
- 16GB > 7B parameter models (int4)
- 32GB > 13B parameter models (int4)
- 8GB → up to 3B parameter models (int4)
- 16GB → up to 7B parameter models (int4)
- 32GB → up to 13B parameter models (int4)
<Callout type="info">
DDR2 RAM is supported but newer RAM generations are recommended for better performance.
</Callout>
- **GPU**:
- 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)
- 6GB → up to 3B parameter models
- 8GB → up to 7B parameter models
- 12GB → up to 13B parameter models
<Callout type="info">
Minimum 6GB VRAM recommended for NVIDIA, AMD, or Intel Arc GPUs.
</Callout>
- **Storage:** Minimum 10GB free space for application and model downloads
@ -153,9 +160,9 @@ Expected output should show your GPU model and driver version.
nvcc --version
```
### Step 2: Enable GPU Acceleration
1. In Jan, navigate to **Settings** > **Hardware**
3. Select and enable your prefered NVIDIA GPU(s)
4. App reload is required after the selection
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
3. App reload is required after the selection
<Callout type="info">
While Jan supports both CUDA and Vulkan for NVIDIA GPUs, we strongly recommend using CUDA for optimal performance.
@ -166,23 +173,32 @@ While Jan supports both CUDA and Vulkan for NVIDIA GPUs, we strongly recommend u
</Tabs.Tab>
<Tabs.Tab>
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
AMD GPUs require **Vulkan** support.
<Callout type="warning">
This feature is currently experimental and must be enabled through [Experimental Mode](/docs/settings#experimental-mode) in **Advanced Settings**.
</Callout>
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. Enable **Experimental Mode**
3. Under **GPU Acceleration**, enable **Vulkan Support**
4. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
5. App reload is required after the selection
</Tabs.Tab>
<Tabs.Tab>
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
Intel Arc GPUs require **Vulkan** support.
<Callout type="warning">
This feature is currently experimental and must be enabled through [Experimental Mode](/docs/settings#experimental-mode) in **Advanced Settings**.
</Callout>
1. Navigate to **Settings** (<Settings width={16} height={16} style={{display:"inline"}}/>) > **Advanced Settings**
2. Enable **Experimental Mode**
3. Under **GPU Acceleration**, enable **Vulkan Support**
4. At **GPU Acceleration**, toggle on and select your preferred GPU(s)
5. App reload is required after the selection
</Tabs.Tab>
</Tabs>
@ -215,6 +231,11 @@ To ensure a complete uninstallation, remove the app cache:
1. Navigate to `C:\Users\[username]\AppData\Roaming`
2. Delete Jan folder
or through **Terminal**:
```
cd C:\Users\%USERNAME%\AppData\Roaming
rmdir /S jan
```
</Steps>
<Callout type="warning">