Bonsai-27B-GGUF is a collection of quantized weights for the Bonsai 27 billion parameter language model, optimized for use with GGUF-compatible local inference engines such as LM Studio, llama.cpp, and Ollama. It enables users to run a capable open-weight LLM entirely on their own machines for privacy, offline access, and customization. The repository on Hugging Face provides multiple quantization levels to balance performance and hardware requirements.
Bonsai 27B is a Foundation models & chat project. It focuses on running large language models locally on consumer hardware without relying on cloud APIs. It is built as an open-source project for developers and AI researchers. Bonsai 27B is open source under the Open Source license. It runs on the web, the command line, and API.
lmstudio-community builds and maintains Bonsai 27B, and it first shipped in 2024. Key capabilities include GGUF Quantization, Local Inference, and Multiple Bit Depths.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do