PS4Research/fQ2tK7dM4rQ9fH3v

TEXT GENERATIONConcurrency Cost:1Model Size:14.7BQuant:FP8Ctx Length:32kPublished:May 12, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

PS4Research/fQ2tK7dM4rQ9fH3v is a 14.7 billion parameter Phi-3 model developed by PS4Research, fine-tuned from unsloth/phi-4-reasoning-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. With a 32768 token context length, it is optimized for efficient processing and reasoning tasks.

Loading preview...

Model Overview

PS4Research/fQ2tK7dM4rQ9fH3v is a 14.7 billion parameter Phi-3 model, developed by PS4Research. It is fine-tuned from the unsloth/phi-4-reasoning-unsloth-bnb-4bit base model, leveraging the Unsloth library for accelerated training.

Key Characteristics

  • Architecture: Based on the Phi-3 model family.
  • Parameter Count: 14.7 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Achieved 2x faster training speeds by utilizing Unsloth and Huggingface's TRL library.

Use Cases

This model is suitable for applications requiring a large context window and efficient processing, particularly benefiting from its accelerated training methodology. Its foundation suggests potential strengths in reasoning tasks, inherited from its base model.