Model serving and local inference
Software that runs AI models efficiently on a server or on a person's own computer.
Includes: Inference servers and local model runners.
For example: Ollama, vLLM, llama.cpp, LM Studio.
10 listed products
| Product | What it says it does |
|---|---|
| Ollama | Use open models in your desktop apps and coding agents, or build them into your application. |
| Jan | Your personal intelligence. Run any model, your way. |
| llamafile | Distribute and run LLMs with a single file. |
| SGLang | High-performance serving framework for large language and multimodal models. |
| vLLM | The High-Throughput and Memory-Efficient inference and serving engine for LLMs |
| llama-cpp-python | Python bindings for llama.cpp |
| llama.cpp | LLM inference in C/C++ |
| LM Studio | The agent for your computer |
| LocalAI | Make AI run on every machine. |
| MLX LM | Run LLMs with MLX |
10 of these are read from their own pages. A product appears where AirStack's category list places it; 7,865 of 13,386 listed products carry no category yet.