> ## Documentation Index
> Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Deploy LFMs

> Choose a framework for local inference or a platform for GPU deployment.

> [card] [llama.cpp](https://docs.liquid.ai/deployment/on-device/llama-cpp.md)
>
> Embed models in your app or run a local API across CPUs and GPUs.

> [card] [Ollama](https://docs.liquid.ai/deployment/on-device/ollama.md)
>
> Get a local model API running with a few commands.

> [card] [MLX](https://docs.liquid.ai/deployment/on-device/mlx.md)
>
> Build Python applications with GPU acceleration on Apple Silicon.

> [card] [vLLM](https://docs.liquid.ai/deployment/gpu-inference/vllm.md)
>
> Handle concurrent requests with continuous batching.

> [card] [SGLang](https://docs.liquid.ai/deployment/gpu-inference/sglang.md)
>
> Serve agents with tool calling and constrained JSON output.

> [card] [Modal](https://docs.liquid.ai/deployment/gpu-inference/modal.md)
>
> Run GPU services that scale without managing servers.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.