Bonsai-27B-gguf is a 27B parameter language model provided in GGUF format for use with llama.cpp and llama-cpp-python. It supports local chat completion, on-device inference across CPU, CUDA, and Metal, and includes hybrid attention optimizations. The model is intended for developers seeking high-performance local AI without relying on remote APIs.
Bonsai 27B sits in PulseGate's Foundation models & chat category. It focuses on running a high-quality 27-billion-parameter language model efficiently on consumer hardware without cloud dependency. Bonsai 27B is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, macOS, Linux, and Windows.
Prism ML builds and maintains Bonsai 27B, and the product first shipped in 2026. The project is developed in the open on GitHub with 2k stars and 30 commits in the last 90 days. PulseGate's similarity index places it among 6 comparable tools. Among its 4 catalogued features are Local Inference, GGUF Format, and Chat Completion.
Latest indexed changes and source events
prism-ml/Bonsai-27B-gguf verified by the PulseGate indexer
Other apps tracked under the same category.
