This is a GGUF-quantized format of the 120-billion parameter GPT-OSS model, optimized by Unsloth for efficient local execution. It enables users to run this large open-weight model on standard hardware using tools like llama.cpp or Ollama.
In the Quantised & converted weights space, Gpt Oss 120b takes a focused approach. It focuses on running a very large 120B open-source language model efficiently on consumer hardware. It is built as an open-source project for developers and researchers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
Behind Gpt Oss 120b is Unsloth, and it first shipped in 2023. Development happens publicly on GitHub with 68.6k stars and 1.2k commits in the last 90 days.
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