FastFlowLM is an open-source runtime designed for efficient local inference of large language models on AMD Ryzen AI NPUs. It offers an Ollama-style developer experience, instant installation, and supports text, vision, and audio models with high power efficiency and large context windows. Ideal for developers seeking fast, private, and on-device AI capabilities.
FastFlowLM sits in PulseGate's AI & ML category. It focuses on running large language models efficiently on AMD Ryzen AI NPUs with instant setup and high power efficiency. It is built as an open-source project for developers working with on-device AI inference and AMD Ryzen AI hardware. FastFlowLM is open source under the MIT license. FastFlowLM is available on the web, Windows, and the command line, and it can be self-hosted.
FastFlowLM first shipped in 2025. Development happens publicly on GitHub with 1.6k stars and 213 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — FastFlowLM occupies a relatively distinct niche. Key capabilities include NPU acceleration, large context window, and vision model support.
Latest indexed changes and source events
Other apps tracked under the same category.
