meissosisai/arc1-mini

TEXT GENERATIONConcurrency Cost:1Model Size:3.8BQuant:BF16Ctx Length:32kPublished:Feb 28, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The meissosisai/arc1-mini is a 3.8 billion parameter Phi-3 model, finetuned by meissosisai from unsloth/phi-4-mini-instruct-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster finetuning. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

The meissosisai/arc1-mini is a 3.8 billion parameter language model, developed by meissosisai. It is a finetuned variant of the Phi-3 architecture, specifically building upon the unsloth/phi-4-mini-instruct-unsloth-bnb-4bit model.

Key Characteristics

  • Architecture: Based on the Phi-3 model family.
  • Parameter Count: 3.8 billion parameters, offering a balance between performance and efficiency.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Context Length: Supports a context window of 32768 tokens.

Intended Use Cases

This model is suitable for a variety of instruction-following applications where a compact yet capable language model is required. Its efficient training process makes it an interesting candidate for developers looking to deploy models with optimized resource usage.