This is a 4-bit quantized version of the gpt-oss-20b model prepared using Unsloth and BitsAndBytes. It is designed for efficient local inference while maintaining high performance. The model includes comprehensive schema handling and is optimized for reduced memory footprint.
Gpt Oss 20b Unsloth Bnb is a Quantised & converted weights project. It focuses on providing an efficient, quantized version of a 20B parameter model for local inference. It is built as an open-source project for developers. The project is open source (Apache-2.0). Gpt Oss 20b Unsloth Bnb is available on the web, the command line, and API.
unsloth builds and maintains Gpt Oss 20b Unsloth Bnb, and it first shipped in 2023. The project is developed in the open on GitHub with 68.7k stars and 1.2k commits in the last 90 days. Key capabilities include 4-bit Quantization, Unsloth Optimized, and bitsAndBytes.
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