text-embeddings-inference documentation
Using TEI locally with Metal
Getting started
Tutorials
Using TEI locally with CPUUsing TEI locally with MetalUsing TEI locally with GPUServing private and gated modelsBuild custom container for TEIUsing TEI container with Intel HardwareUsing TEI on AMD Instinct GPUs (ROCm)Example uses
Deploying TEI on Google Cloud
Reference
Using TEI locally with Metal
You can install text-embeddings-inference locally to run it on your own Mac with Metal support.
Homebrew (Apple Silicon)
On Apple Silicon (M1/M2/M3/M4), you can install a prebuilt binary via Homebrew:
brew install text-embeddings-inference
Then launch Text Embeddings Inference:
model=Qwen/Qwen3-Embedding-0.6B text-embeddings-router --model-id $model --port 8080
Build from source
Alternatively, you can build from source. Here are the step-by-step instructions:
Step 1: Install Rust
Install Rust on your machine by run the following in your terminal, then following the instructions:
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
Step 2: Install with Metal support
cargo install --path router -F metal
Step 3: Launch Text Embeddings Inference
Once the installation is successfully complete, you can launch Text Embeddings Inference with Metal with the following command:
model=Qwen/Qwen3-Embedding-0.6B text-embeddings-router --model-id $model --port 8080
Now you are ready to use text-embeddings-inference locally on your machine.