PS4Research/TFDDn0MkziaAlcn0

TEXT GENERATIONPricing:Input $0.48 / Output $0.96Concurrent Unit Cost:1Model Size:14BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 27, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

PS4Research/TFDDn0MkziaAlcn0 is a 14 billion parameter Qwen3 model developed by PS4Research. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language tasks, leveraging its Qwen3 architecture for efficient performance.

Loading preview...

Model Overview

PS4Research/TFDDn0MkziaAlcn0 is a 14 billion parameter Qwen3 model developed by PS4Research. This model has been finetuned from unsloth/Qwen3-14B-bnb-4bit and utilizes the Unsloth library in conjunction with Huggingface's TRL library. This combination allowed for a significant acceleration in the training process, achieving 2x faster finetuning.

Key Characteristics

  • Architecture: Based on the Qwen3 model family.
  • Parameter Count: 14 billion parameters.
  • Training Efficiency: Finetuned with Unsloth and Huggingface TRL for 2x faster training.
  • License: Released under the Apache-2.0 license.

Intended Use Cases

This model is suitable for a variety of general language generation and understanding tasks, benefiting from its efficient finetuning process and the capabilities of the Qwen3 architecture. Developers looking for a Qwen3-based model that has undergone optimized training may find this model particularly useful.

Finetunes
2 models