anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Jun 21, 2025Architecture:Transformer0.0K Warm
anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only is a 24 billion parameter instruction-tuned language model based on the standard Mistral architecture. This model is a text-only variant of Mistral Small 3.2, specifically designed without a vision encoder. It offers a 32,768 token context window, making it suitable for complex text generation and understanding tasks.
Loading preview...
Model Overview
anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only is an instruction-tuned language model with 24 billion parameters, built upon the established Mistral architecture. This particular variant is distinguished by its exclusive focus on text processing, as it has been modified to operate without a vision encoder.
Key Capabilities
- Text-Only Processing: Optimized for natural language understanding and generation tasks, without multimodal capabilities.
- Standard Mistral Architecture: Leverages the robust and efficient design principles of the Mistral family of models.
- Large Context Window: Features a 32,768 token context length, enabling the processing of extensive documents and complex conversational histories.
Good For
- Applications requiring deep textual analysis and generation.
- Instruction-following tasks where multimodal input is not necessary.
- Scenarios benefiting from a large context window for comprehensive text processing.