Alelcv27/Llama3.2-3B-Arcee-Math-Code

TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Apr 20, 2026Architecture:Transformer Cold

Alelcv27/Llama3.2-3B-Arcee-Math-Code is a 3.2 billion parameter language model, merged using the Arcee Fusion method from Alelcv27's Llama3.2-3B-Base-Math and Llama3.2-3B-Base-Code models. This model is specifically optimized for enhanced performance in both mathematical reasoning and code generation tasks. It leverages a 32768 token context length to handle complex problems in these domains. The model is designed for developers requiring a compact yet capable solution for specialized math and coding applications.

Loading preview...

Model Overview

Alelcv27/Llama3.2-3B-Arcee-Math-Code is a 3.2 billion parameter language model, developed by Alelcv27, that integrates capabilities from two specialized base models. It was created using the Arcee Fusion merge method, combining Alelcv27/Llama3.2-3B-Base-Math and Alelcv27/Llama3.2-3B-Base-Code.

Key Capabilities

  • Specialized Fusion: This model is a direct merge of a math-focused base model and a code-focused base model, aiming for combined proficiency in both areas.
  • Mathematical Reasoning: Inherits and enhances capabilities for handling mathematical problems and logical reasoning.
  • Code Generation: Designed to perform effectively in generating and understanding code.
  • Efficient Size: At 3.2 billion parameters, it offers a balance between performance and computational efficiency.

Good For

  • Applications requiring a blend of mathematical problem-solving and code generation.
  • Developers looking for a compact model optimized for specific technical tasks.
  • Use cases where a dedicated focus on math and code performance is critical.