Ternary-Bonsai-27B-mlx-2bit is a quantized 27B parameter language model optimized for efficient inference using MLX. It enables local deployment with reduced memory requirements, making large language models more accessible for research and development.
Ternary Bonsai 27B is a Foundation models & chat product. It focuses on enabling efficient, low-memory inference of large language models on local hardware. It is built as an open-source project for machine learning engineers and researchers. Ternary Bonsai 27B is open source under the Apache-2.0 license. Ternary Bonsai 27B is available on the command line, and it can be self-hosted.
It is developed by thoddnn, and the product first shipped in 2026. Development happens publicly on GitHub with 1.1k stars and 27 commits in the last 90 days. Key capabilities include quantized inference, text generation, and MLX compatibility.
Latest indexed changes and source events
thoddnn/Ternary-Bonsai-27B-mlx-2bit verified by the PulseGate indexer
Other apps tracked under the same category.
