Devstral-Small-2-24B-Instruct-2512-4bit is a 4-bit quantized version of a 24-billion-parameter instruction-tuned language model, optimized for the MLX framework on Apple hardware. It is distributed by the MLX community on Hugging Face and supports efficient local inference with a custom chat template.
Devstral Small 2 24B Instruct 2512 sits in PulseGate's Text generation category. It focuses on running a capable 24B parameter instruction model efficiently on Apple silicon using MLX. It is built as an open-source project for developers. Devstral Small 2 24B Instruct 2512 is open source under the Open Source license. It runs on the web, the command line, and API.
Behind Devstral Small 2 24B Instruct 2512 is MLX Community. Key capabilities include Instruction Tuned, 4-bit Quantized, and 24B Parameters.
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