Hy3-GGUF is a repository of GGUF-quantized weights for the Hy3 language model. It includes specialized tokenization for tool calling, thinking steps, and structured conversations. The files are designed for use with local inference engines such as llama.cpp or LM Studio, enabling efficient on-device or self-hosted LLM usage.
Hy3 is a Foundation models & chat project. It focuses on running high-performance language models locally with efficient quantized GGUF format. Hy3 is an open-source project aimed at developers. Hy3 is open source under the MIT license. Hy3 is available on the web, the command line, and API.
bartowski builds and maintains Hy3, and it first shipped in 2023. Development happens publicly on GitHub with 121.8k stars and 1.2k commits in the last 90 days. Among its 3 catalogued features are GGUF Quantization, Custom Tokenizer, and Tool Calling Support.
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