PS4Research/xE6nV9hA5yW1jT7s
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kPublished:May 7, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
PS4Research/xE6nV9hA5yW1jT7s is a 14 billion parameter Qwen3-based language model developed by PS4Research, fine-tuned from unsloth/Qwen3-14B-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. With a 32768 token context length, it is optimized for applications requiring efficient fine-tuning and deployment of Qwen3 architecture.
Loading preview...
Model Overview
PS4Research/xE6nV9hA5yW1jT7s is a 14 billion parameter language model developed by PS4Research. It is a fine-tuned variant of the Qwen3 architecture, specifically built upon the unsloth/Qwen3-14B-bnb-4bit base model.
Key Characteristics
- Architecture: Based on the Qwen3 model family.
- Parameter Count: 14 billion parameters.
- Context Length: Supports a substantial context window of 32768 tokens.
- Training Efficiency: This model was fine-tuned with significant speed improvements, achieving 2x faster training by leveraging the Unsloth library in conjunction with Huggingface's TRL library.
Use Cases
This model is particularly well-suited for developers and researchers looking for:
- Efficiently fine-tuned Qwen3-based models.
- Applications requiring a 14B parameter model with a large context window.
- Projects benefiting from the performance and training optimizations offered by Unsloth.