Installation

Install llmfit on macOS, Linux, or Windows

llmfit is distributed as a single binary with no runtime dependencies. Choose your preferred installation method below.

macOS

Homebrew (recommended)

Install via Homebrew:

brew install llmfit

This installs the latest stable release and keeps llmfit updated with brew upgrade.

curl install script

Alternatively, use the quick install script:

curl -fsSL https://llmfit.axjns.dev/install.sh | sh

This downloads the latest release binary from GitHub and installs it to /usr/local/bin.

Install without sudo (installs to ~/.local/bin):

curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local

Make sure ~/.local/bin is in your $PATH. Add export PATH="$HOME/.local/bin:$PATH" to your shell profile if needed.

Linux

curl install script (recommended)

Install via the quick install script:

curl -fsSL https://llmfit.axjns.dev/install.sh | sh

This downloads the latest release binary and installs it to /usr/local/bin (requires sudo).

Install without sudo (installs to ~/.local/bin):

curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local

Make sure ~/.local/bin is in your $PATH. Add export PATH="$HOME/.local/bin:$PATH" to your .bashrc or .zshrc.

Manual installation

1. Download the latest release for your architecture from GitHub Releases
2. Extract the tarball:
   tar -xzf llmfit-*-unknown-linux-musl.tar.gz
   
3. Move the binary to a directory in your $PATH:
   sudo mv llmfit /usr/local/bin/
   # Or without sudo:
   mkdir -p ~/.local/bin && mv llmfit ~/.local/bin/
   
4. Verify installation:
   llmfit --version
   

Windows

Scoop (recommended)

Install via Scoop:

scoop install llmfit

If Scoop is not installed, follow the Scoop installation guide.

Manual installation

1. Download the latest Windows release from GitHub Releases
2. Extract the ZIP archive
3. Add the extracted directory to your PATH environment variable
4. Open a new terminal and verify:
   llmfit --version
   

Build from source

Build the latest development version from source using Rust:

1. Install Rust

   If you don’t have Rust installed, get it from rustup.rs:

   curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
   

   Ensure you have Rust 1.85+ (edition 2024 support).

2. Clone and build

   Clone the repository and build the release binary:

   git clone https://github.com/AlexsJones/llmfit.git
   cd llmfit
   cargo build --release
   

   The compiled binary will be at target/release/llmfit.

3. Install the binary

   Move the binary to a directory in your $PATH:

   # macOS/Linux
   sudo mv target/release/llmfit /usr/local/bin/
   
   # Or without sudo
   mkdir -p ~/.local/bin && mv target/release/llmfit ~/.local/bin/
   

   On Windows, move target\release\llmfit.exe to a directory in your PATH.

4. Verify installation

   Confirm llmfit is working:

   llmfit --version
   

System requirements

Minimum requirements

• OS: Linux (x86_64, aarch64), macOS (Intel, Apple Silicon), or Windows (x86_64)
• RAM: No specific requirement (llmfit itself uses less than 50 MB)
• Disk: ~10 MB for the binary

Optional: GPU detection tools

For GPU detection to work, install the appropriate tool for your hardware:

GPU Vendor	Detection Tool	Purpose
NVIDIA	nvidia-smi	VRAM reporting, multi-GPU support
AMD	rocm-smi	ROCm GPU detection
Intel Arc	sysfs, lspci	Discrete/integrated GPU detection
Apple Silicon	system_profiler	Unified memory reporting (built-in)
Ascend	npu-smi	NPU detection

GPU detection is best-effort. If autodetection fails, use llmfit --memory=24G to manually specify your VRAM size.

Optional: Runtime providers

To download and run models from the TUI, install a runtime provider:

• Ollama: Download from ollama.com (macOS, Linux, Windows)
• llama.cpp: Build from github.com/ggml-org/llama.cpp or install via package manager
• MLX: Install via pip on Apple Silicon: pip install mlx-lm

llmfit works without these tools installed — you just won’t be able to download or detect installed models.

Verify installation

After installing, verify llmfit is working:

# Check version
llmfit --version

# Display system specs
llmfit system

# Launch TUI
llmfit

You should see your hardware specs (RAM, CPU cores, GPU name and VRAM).

Troubleshooting

Command not found

If you see command not found: llmfit, the binary is not in your $PATH:

1. Check where llmfit is installed:
   which llmfit
   
2. If it’s in ~/.local/bin, add this to your shell profile (~/.bashrc, ~/.zshrc, etc.):
   export PATH="$HOME/.local/bin:$PATH"
   
3. Reload your shell:
   source ~/.bashrc  # or ~/.zshrc
   

GPU not detected

If your GPU is not detected:

1. Check if the detection tool is installed:
   # NVIDIA
   nvidia-smi
   
   # AMD
   rocm-smi
   
2. If the tool is missing, install it via your package manager or GPU vendor’s website
3. If detection still fails, manually specify VRAM:
   llmfit --memory=24G
   

Incorrect VRAM reported

On some systems (VMs, passthrough setups, broken drivers), VRAM autodetection may fail or report incorrect values. Override with --memory:

# Specify 32 GB VRAM
llmfit --memory=32G

# Works with all modes
llmfit --memory=24G --cli
llmfit --memory=24G fit --perfect -n 5

Accepted suffixes: G/GB/GiB (gigabytes), M/MB/MiB (megabytes), T/TB/TiB (terabytes). Case-insensitive.

Permission denied (install script)

If the install script fails with permission denied:

1. Try the --local flag to install without sudo:
   curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local
   
2. Make sure ~/.local/bin is in your $PATH

Update llmfit

Update to the latest version using the same method you used to install:

Homebrew (macOS/Linux)

brew upgrade llmfit

Scoop (Windows)

scoop update llmfit

curl install script

curl -fsSL https://llmfit.axjns.dev/install.sh | sh

The script always installs the latest release.

From source

cd llmfit
git pull
cargo build --release
sudo mv target/release/llmfit /usr/local/bin/

Uninstall

Remove llmfit by deleting the binary:

Homebrew

brew uninstall llmfit

Scoop

scoop uninstall llmfit

Manual

# Find where it's installed
which llmfit

# Remove the binary
sudo rm /usr/local/bin/llmfit
# Or if installed locally:
rm ~/.local/bin/llmfit

Optionally, remove config files:

rm -rf ~/.config/llmfit

Next steps

Quickstart

Get from installation to first successful run

TUI Mode

Learn keyboard shortcuts and navigation

CLI Mode

Use llmfit in scripts and automation

System Commands

Check detected hardware specs