This is an int8 quantized version of Mistral Small 3.2 24B Instruct, optimized for local inference. It includes a chat template and supports tool calling, making it suitable for building AI assistants and agents. The model is available on Hugging Face and can be used with transformers or llama.cpp for efficient on-device or server deployment.
Mistral Small 3.2 24B Instruct 2506 is a Tool calling project. It focuses on running powerful instruction-tuned language models locally with reduced memory requirements. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web and the command line, and it can be self-hosted.
Behind Mistral Small 3.2 24B Instruct 2506 is documentazione. Among its 4 catalogued features are instruction tuned, quantized model, and chat template.
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