anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Jun 20, 2025Architecture:Transformer0.0K Warm

The anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML is a 24 billion parameter instruction-tuned language model based on the standard Mistral architecture. This model is a modified version of Mistral Small 3.2, specifically adapted for ChatML formatting by reusing special tokens. It is designed for general conversational AI and instruction-following tasks, without a vision encoder.

Loading preview...

Model Overview

The anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML is a 24 billion parameter instruction-tuned language model. It is built upon the standard Mistral architecture, providing a robust foundation for various natural language processing tasks. This particular iteration is a modified version of Mistral Small 3.2, tailored for specific use cases.

Key Characteristics

  • Architecture: Utilizes the standard Mistral architecture, known for its efficiency and performance.
  • Parameter Count: Features 24 billion parameters, offering a balance between capability and computational requirements.
  • Context Length: Supports a context window of 32768 tokens, enabling processing of longer inputs and maintaining conversational coherence.
  • ChatML Adaptation: Specifically modified to support ChatML formatting, making it suitable for chat-based applications and instruction following.
  • No Vision Encoder: Unlike some multimodal models, this version does not include a vision encoder, focusing purely on text-based understanding and generation.

Intended Use Cases

This model is well-suited for applications requiring:

  • Instruction Following: Excels at understanding and executing user instructions in a conversational context.
  • General Chat Applications: Ideal for building chatbots, virtual assistants, and interactive dialogue systems.
  • Text Generation: Capable of generating coherent and contextually relevant text based on prompts.
  • Developers using ChatML: Optimized for integration into systems that leverage the ChatML format for structured conversations.