Marmot is an open-source LLM inference engine written in modern C23, designed for high-performance local execution of GGUF models. It supports multiple quantization formats, CPU and Metal backends, and provides a CLI for easy model management and inference. Ideal for developers and researchers needing local LLM capabilities.
Marmot is a Foundation models & chat product. It focuses on running large language models efficiently on local hardware without cloud dependencies. It is built as an open-source project for developers and AI researchers. Marmot is open source under the MIT license. Marmot is available on the command line.
Marmot Maintainers (GitHub) builds and maintains Marmot, and the product first shipped in 2024. Development happens publicly on GitHub with 585 stars and 102 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Marmot occupies a relatively distinct niche. Key capabilities include LLM inference, GGUF model support, and CPU and Metal backends.
Latest indexed changes and source events
Other apps tracked under the same category.
