Open-source DeepInfra alternatives

Ollama makes it straightforward to run open large language models on your own machine. You install it on macOS, Windows or Linux, or use the official Docker image, then pull a model and chat with it from the command line. It is written in Go and released under the MIT license, and it builds on the llama.cpp project for inference.

Besides the CLI, Ollama provides a REST API for managing and running models, with official Python and JavaScript client libraries. Models can be imported and customized through a Modelfile, and an online library lists what is available. It can be connected to coding agents and assistants such as Claude Code, OpenCode, Codex and OpenClaw, and many community chat interfaces, including Open WebUI and LibreChat, work with it.

Because models run on your own hardware, Ollama can serve as a self-hosted alternative to cloud assistants such as ChatGPT and Perplexity when privacy, offline use or cost control matter. It is aimed at developers and hobbyists experimenting with open models, and at teams that want to wire local models into their own applications.

vLLM is an open-source library for running and serving large language models efficiently. It originated at UC Berkeley's Sky Computing Lab and is now developed by a large community of contributors from academia and industry. It is written in Python and released under the Apache-2.0 license.

Speed comes from techniques such as PagedAttention for attention key-value memory, batching incoming requests continuously, chunked prefill, prefix caching, CUDA and HIP graphs, and optimized attention and mixture-of-experts kernels. It supports many quantization formats, including FP8, INT8, INT4, GPTQ and AWQ, as well as speculative decoding and disaggregated prefill and decode.

On the usability side, vLLM integrates with Hugging Face models and supports parallel sampling, beam search, streaming outputs, structured outputs and tool calling, plus several parallelism modes (tensor, pipeline, data, expert and context) for distributed inference. It targets NVIDIA, AMD and TPU hardware and suits teams that serve open models in production and need high throughput.

LocalAI is an open-source AI engine for running models of many kinds, including language, vision, voice, image and video models, on your own hardware. A GPU is not required. It is written in Go and released under the MIT license, was started by Ettore Di Giacinto and is looked after by the LocalAI team.

Its design is a small core with separate backends that are pulled on demand, so nothing unused gets installed. Backends wrap engines such as llama.cpp, vLLM, whisper.cpp, stable-diffusion and MLX, and you can write your own in any language against an open interface. It can run on CPU alone, through Vulkan, or on NVIDIA, AMD, Intel and Apple Silicon hardware.

APIs are drop-in compatible with OpenAI, Anthropic and ElevenLabs across every backend. Multi-user features include API key authentication, user quotas and role-based access, and built-in agents support tool use, RAG, MCP and skills. The project stresses that data stays on your infrastructure. It suits developers and teams who want a private, self-hosted replacement for cloud AI APIs.

SGLang is an inference framework, released as open source, for language models, vision-language models and diffusion models. It is optimized for agentic workloads, reinforcement-learning rollouts and large-scale serving. The project includes SGLang Diffusion, a built-in engine for image and video generation that ships in the same repository and Python package. It is released under the Apache-2.0 license.

Getting started takes either a prebuilt Docker image or a Python install using uv, followed by a launch command for the chosen model. A cookbook helps pick a model and hardware pair and generates a ready-to-run command. Supported hardware spans NVIDIA and AMD GPUs, Google TPUs, Intel GPUs and CPUs, Apple Silicon through Metal and MLX, and Huawei Ascend NPUs, with more integrations in progress. The wider SGLang ecosystem adds educational projects and community events.