This is a 4-bit AWQ quantized version of a 24B parameter instruct model derived from the Mistral3 architecture. It is optimized for local inference and excels at coding and technical tasks. The model is distributed on Hugging Face for use with Transformers or compatible inference engines.
In the Foundation models & chat space, Devstral Small 2 24B Instruct 2512 takes a focused approach. It focuses on running a capable coding-focused large language model locally with reduced memory requirements. Devstral Small 2 24B Instruct 2512 is an open-source project aimed at developers. The project is open source (Apache-2.0). Devstral Small 2 24B Instruct 2512 is available on the web, the command line, and API.
It is developed by cyankiwi, and the product first shipped in 2025. The project is developed in the open on GitHub with 4.7k stars and 32 commits in the last 90 days. Among its 3 catalogued features are instruct-tuned, 4-bit Quantized, and Code Generation.
Latest indexed changes and source events
cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit verified by the PulseGate indexer
