PS4Research/eP9pL3xJ8gD6cY5n

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:May 16, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

PS4Research/eP9pL3xJ8gD6cY5n is a 24 billion parameter Mistral-based language model developed by PS4Research, fine-tuned from unsloth/Magistral-Small-2506-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling a 2x faster fine-tuning process. It is designed for general language tasks, leveraging its Mistral architecture and efficient training methodology.

Loading preview...

Model Overview

PS4Research/eP9pL3xJ8gD6cY5n is a 24 billion parameter language model developed by PS4Research. It is a fine-tuned variant of the unsloth/Magistral-Small-2506-unsloth-bnb-4bit model, leveraging the Mistral architecture.

Key Characteristics

  • Efficient Fine-tuning: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Mistral Base: Built upon the Mistral architecture, it inherits the strong performance characteristics associated with this family of models.
  • Parameter Count: With 24 billion parameters, it offers a balance between capability and computational requirements for various NLP tasks.

Potential Use Cases

Given its general-purpose fine-tuning and Mistral base, this model is suitable for a range of applications, including:

  • Text generation and completion
  • Question answering
  • Summarization
  • Chatbot development