This repository by MaziyarPanahi hosts GGUF-quantized versions of the Ministral 3B Reasoning model (dated 2512). It allows users to run a small but capable reasoning-focused LLM on consumer GPUs or CPUs using standard tools like llama.cpp. Multiple quantization levels are provided to balance performance and resource usage.
Ministral 3 3B Reasoning 2512 sits in PulseGate's Foundation models & chat category. It focuses on running a compact, reasoning-capable language model locally with flexible quantization to fit various hardware setups. Ministral 3 3B Reasoning 2512 is an open-source project aimed at developers. Ministral 3 3B Reasoning 2512 is open source under the MIT license. It ships for the web, the command line, and API, and it can be self-hosted.
Behind Ministral 3 3B Reasoning 2512 is MaziyarPanahi, and it first shipped in 2023. The project is developed in the open on GitHub with 122.3k stars and 1.2k commits in the last 90 days. Key capabilities include GGUF formats, reasoning model, and quantized variants. It exposes integrations via a public API.
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