Skip to main content

System Requirements

Jan runs on macOS, Windows, and Linux. Requirements vary based on the size of models you want to run.

Operating System Requirements

macOS

Minimum: macOS 13.6 (Ventura) or laterRecommended: macOS 14+ (Sonoma)Architecture: Intel or Apple Silicon

Windows

Minimum: Windows 10 (64-bit)Recommended: Windows 11GPU Support: NVIDIA, AMD, Intel Arc

Linux

Supported: Most distributionsTested: Ubuntu 18.04+, Debian, FedoraGPU Support: NVIDIA (CUDA 11.7+)

RAM Requirements by Model Size

Choose models based on your available RAM. For best performance, use models that consume less than 80% of your system RAM.

Small Models (3B parameters)

Model Size: 2-4GBExamples:
  • Llama 3B
  • Phi-2
  • Gemma 2B
Performance:
  • Good for basic conversations
  • Lightweight coding assistance
  • Fast response times
Avoid models larger than 6GB with 8GB RAM systems.

GPU Requirements (Optional)

GPU acceleration significantly improves performance but is not required.

NVIDIA GPUs

Requirements:
  • NVIDIA GPU (GTX 10 series or newer recommended)
  • NVIDIA Driver 470.63.01 or higher
  • CUDA Toolkit 11.7 or higher
Installation:
  1. Download NVIDIA Driver
  2. Install CUDA Toolkit
  3. Restart your computer
  4. Launch Jan - GPU will be detected automatically
Verify Installation:
nvidia-smi
nvcc --version

AMD GPUs (Windows)

Requirements:
  • AMD Radeon GPU (RX 5000 series or newer)
  • Latest AMD Adrenalin drivers
Note: AMD support is experimental. Performance may vary.

Intel Arc (Windows)

Requirements:
  • Intel Arc A-series GPU
  • Latest Intel Graphics drivers
Note: Intel Arc support is experimental.

Apple Silicon (macOS)

Built-in Acceleration:
  • M1, M2, M3, M4 chips have automatic Metal acceleration
  • No additional setup required
  • Excellent performance for model size

Verified Configurations

These setups have been tested and confirmed working:

Desktop Configurations

ComponentSpecification
OSWindows 11 Pro 64-bit
GPUNVIDIA GeForce RTX 4070Ti
CUDA12.2
Driver531.18
RAM32GB
Performance: Excellent for 13B-70B models

Virtual Machine Setups

VM performance is typically lower than bare metal installations.
Ubuntu on Proxmox:
ComponentSpecification
OSUbuntu 20.04/18.04 LTS
VMProxmox
GPUNVIDIA GeForce GTX 1660Ti (passthrough)
CUDA12.1
Driver535
Requirements for GPU Passthrough:
  • IOMMU support enabled in BIOS
  • Proper GPU passthrough configuration
  • Dedicated GPU for VM

Storage Requirements

Application Size

  • Jan Installation: 500MB - 1GB
  • System Dependencies: 2-5GB (CUDA, drivers, etc.)

Model Storage

Plan disk space based on models you want:
Model SizeDisk Space Needed
3B models2-4GB per model
7B models4-8GB per model
13B models8-16GB per model
70B models40-80GB per model
Recommended Free Space: 50GB+ for comfortable model collection Storage Location:
  • macOS: ~/Library/Application Support/Jan
  • Windows: C:\Users\%USERNAME%\AppData\Roaming\Jan
  • Linux: ~/.config/Jan

Network Requirements

For Local Models

  • Internet: Only needed to download models initially
  • Offline Use: Fully functional once models are downloaded

For Cloud Integrations

  • Internet: Required for OpenAI, Anthropic, Groq connections
  • Bandwidth: Standard broadband sufficient

Performance Optimization

CPU-Only Systems

  • Use smaller models (3B-7B)
  • Increase CPU threads in settings
  • Close other applications
  • Use SSDs for model storage

GPU-Accelerated Systems

  • Adjust GPU layers (ngl) parameter
  • Start low and increase gradually
  • Monitor VRAM usage
  • Keep 1-2GB VRAM free for system

Compatibility Notes

Laptop Considerations

  • Laptop GPUs may have lower performance than desktop equivalents
  • Thermal throttling can affect sustained performance
  • Hybrid graphics (Optimus) may require additional configuration

Virtual RAM / Swap

  • Not recommended as primary RAM for models
  • Significantly slower than physical RAM
  • May cause poor performance

Quick Reference

Most users: 16GB RAM + 7B models = great experienceBudget systems: 8GB RAM + 3B models = functionalPower users: 32GB+ RAM + GPU + 13B-70B models = excellent

Check Your System

Before installing:
  1. Check RAM:
    • Windows: Task Manager → Performance → Memory
    • macOS: About This Mac → Memory
    • Linux: free -h
  2. Check GPU (if applicable):
    • Windows: Task Manager → Performance → GPU
    • macOS: Apple Silicon includes integrated GPU
    • Linux: lspci | grep -i vga
  3. Check Storage:
    • Ensure 50GB+ free space for models
    • SSD recommended for best performance

Need Help?

If you’re unsure about compatibility:

Build docs developers (and LLMs) love