Llama 2 LLM on DOS is an open-source project that enables users to run Meta's Llama 2 language model locally on vintage DOS-based PCs. It provides a DOS-compatible client for text generation, allowing retrocomputing enthusiasts to experiment with LLMs on legacy hardware without relying on cloud services. The project is fully open source and supports a range of DOS machines.
Llama 2 LLM on DOS sits in PulseGate's AI & ML category. It focuses on running modern large language models locally on vintage DOS computers without internet connectivity. It is built as an open-source project for retrocomputing enthusiasts. Llama 2 LLM on DOS is open source under the MIT license. The product ships for the web, Windows, Linux, and the command line, and it can be self-hosted.
Yeo Kheng Meng builds and maintains Llama 2 LLM on DOS, and the product first shipped in 2023. Development happens publicly on GitHub with 30 stars. Key capabilities include DOS support, local inference, and open source.
Latest indexed changes and source events
Llama 2 LLM on DOS (2025) verified by the PulseGate indexer