Pre-check: open Task Manager → Performance to see RAM and GPU. Then run this in Command Prompt to see GPU name, driver version and VRAM. Also check free disk space.
nvidia-smi
Do you see your GPU name and "Driver Version"?
Download the Windows installer from jan.ai and install it.
Jan opened?
Download a small model (3B–4B, Q4) from the Hub/Models section. Jan hints which models fit your RAM.
Model downloaded?
Start a new chat, pick the model and ask. You can enable GPU acceleration (Vulkan/CUDA) in Settings.
Got a reply?
Pre-check: Task Manager → Performance → GPU shows "AMD Radeon …" and dedicated GPU memory (VRAM). Update the driver with AMD Software: Adrenalin (amd.com).
Can you see the GPU name and VRAM?
Install from jan.ai. AMD GPUs run through Vulkan in Jan.
Jan opened?
Download a small model (3B–4B, Q4) from the Hub/Models section. Jan hints which models fit your RAM.
Model downloaded?
Start a new chat, pick the model and ask. You can enable GPU acceleration (Vulkan/CUDA) in Settings.
Got a reply?
Pre-check: Apple menu → About This Mac. Note the Chip (Apple M-series or Intel), Memory (RAM) and macOS version.
Noted chip, memory and macOS version?
Download the macOS .dmg from jan.ai and drag it to Applications.
Jan opened?
Download a small model (3B–4B, Q4) from the Hub/Models section. Jan hints which models fit your RAM.
Model downloaded?
Start a new chat, pick the model and ask. You can enable GPU acceleration (Vulkan/CUDA) in Settings.
Got a reply?
Pre-check: check RAM, disk and GPU in a terminal.
free -h
df -h ~
lspci | grep -i -E "vga|3d"
See RAM, free disk and GPU name?
Download the .deb (Ubuntu/Debian) or AppImage from jan.ai. Install the .deb, or make the AppImage executable and run it.
Download a small model (3B–4B, Q4) from the Hub/Models section. Jan hints which models fit your RAM.
Model downloaded?
Start a new chat, pick the model and ask. You can enable GPU acceleration (Vulkan/CUDA) in Settings.
Got a reply?
Pre-check: see your RAM (Task Manager / About This Mac / free -h). Small tools run without a GPU — just slower.
Know how much RAM you have?
Install as in your OS tab. Without a GPU, Jan runs on CPU — choose 1B–3B models.
Small model answering?
Start a new chat, pick the model and ask. You can enable GPU acceleration (Vulkan/CUDA) in Settings.
Got a reply?
Sizes are approximate and can change on the official page.
Errors & fixes
Model fails to start / "Failed to load model"
Not enough memory — try a smaller model, close apps, or toggle GPU acceleration off in Settings.
Linux AppImage: "dlopen(): error loading libfuse.so.2"
Ubuntu 22.04: sudo apt install libfuse2 · Ubuntu 24.04: sudo apt install libfuse2t64. Then chmod +x and run.
"Windows protected your PC" (SmartScreen)
Windows shows this for new apps. Continue only if you downloaded from the official link above: More info → Run anyway.
Mac: "cannot be opened because the developer cannot be verified"
System Settings → Privacy & Security → "Open Anyway" — only for the official download.
Download stuck / very slow / "connection reset"
Network or DNS issue. Restart the router, try a mobile hotspot, or set DNS to 1.1.1.1 / 8.8.8.8. Re-running the same command usually resumes the download.
Stars, license and last update come from GitHub (17 Nov 2026). Commands are copied from official docs and are not tested on a real machine yet. Access tags are our summary — always check the source. Skills for every AI →