This repository contains GGUF quantized weights for the GPT-OSS-20B model, making it compatible with LM Studio, llama.cpp, and other GGUF runtimes. It allows users to run a fully open-source 20-billion-parameter language model on local hardware with manageable memory usage. The model is intended for developers and researchers exploring open large language models.
Gpt Oss 20b is a Quantised & converted weights project. It focuses on running a capable open-source 20B LLM locally with reduced resource requirements using GGUF quantization. It is built as an open-source project for AI developers. Gpt Oss 20b is open source under the MIT license. It runs on the command line.
Behind Gpt Oss 20b is lmstudio-community, and it first shipped in 2023. The project is developed in the open on GitHub with 121.2k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 6 similar projects. Key capabilities include GGUF Format, 20B Parameters, and Local LLM.
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