Model Card for Magistral Small 2506 FP8 This checkpoint is the FP8 W8A8 quantized version of mistralai/Magistral Small 2506, compressed using the Mistral format integration in LLM Compressor. It is important to note that this is a Mistral format checkpoint, so it must be run in vLLM with tokenizer mode mistral config format mistral load format mistral . For instance, serve the model as follows: Evaluation GSM8k: Original Model Card Building upon Mistral Small 3.1 (2503), with added reasoning capabilities , undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters. Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized. Learn more about Magistral in our blog post. Key Features Reasoning: Capable of long chains of reasoning traces before providing an answer. Multilingual: Supports dozens of languages, including English, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Nepali, Polish, Portuguese, Romanian, Russian, Serbian, Spanish, Swedish, Turkish, Ukrainian, Vietnamese, Arabic, Bengali, Chinese, and Farsi. Apache 2.0 License: Open license a…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy