ZeroAgency/Mistral-Small-3.2-24B-Instruct-2506-Text-Only

TEXT GENERATIONConcurrent Unit Cost:2Model Size:24BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 23, 2025Architecture:Transformer0.0K Featherless Exclusive Cold

ZeroAgency/Mistral-Small-3.2-24B-Instruct-2506-Text-Only is a 24 billion parameter instruction-tuned language model based on the standard Mistral architecture. Derived from anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only, this variant has been modified to exclude a vision encoder and incorporates the 3.2 system prompt in its chat template. It is designed for text-only applications, offering a 32768 token context length.

Loading preview...

Overview

ZeroAgency/Mistral-Small-3.2-24B-Instruct-2506-Text-Only is a 24 billion parameter instruction-tuned language model. It is a modified version of the anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only model, specifically adapted for text-only applications.

Key Characteristics

  • Architecture: Utilizes the standard Mistral architecture.
  • Parameter Count: Features 24 billion parameters.
  • Context Length: Supports a context window of 32768 tokens.
  • Vision Capabilities: This variant explicitly excludes a vision encoder, making it optimized solely for text-based tasks.
  • Instruction Tuning: Incorporates the system prompt from the 3.2 version directly into its default chat template, enhancing its instruction-following capabilities.

Good For

This model is suitable for developers and applications requiring a robust, instruction-tuned language model focused exclusively on text processing. Its modifications make it a streamlined choice for scenarios where vision capabilities are not needed, potentially offering efficiency for text-centric workloads.

Finetunes
1 models