quantfit is an open-source command-line tool that enables users to quantize large language models (LLMs) for efficient GPU inference while ensuring safety compliance. It is designed for AI researchers and engineers working with custom or open-source LLMs.
In the Other AI space, quantfit takes a focused approach. It focuses on making it easy to quantize large language models and verify their safety on local GPUs. quantfit is an open-source project aimed at AI researchers and ML engineers. quantfit is open source under the Apache-2.0 license. It ships for the command line.
Sahil170595 builds and maintains quantfit, and it first shipped in 2026. Development happens publicly on GitHub with 20 commits in the last 90 days. Among its 4 catalogued features are LLM quantization, safety compliance check, and GPU 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