Murgic/Ether14b
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 24, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold
Murgic/Ether14b is a Qwen3-based language model developed by Murgic, fine-tuned from unsloth/Qwen3-32B-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general language tasks, leveraging the Qwen3 architecture for efficient performance.
Loading preview...
Overview
Murgic/Ether14b is a fine-tuned language model based on the Qwen3 architecture, specifically derived from the unsloth/Qwen3-32B-bnb-4bit model. Developed by Murgic, this model leverages advanced training techniques to optimize performance and efficiency.
Key Capabilities
- Efficient Training: The model was trained 2x faster by utilizing Unsloth and Huggingface's TRL library, indicating a focus on optimized resource usage during development.
- Qwen3 Foundation: Built upon the Qwen3 base model, it inherits the general language understanding and generation capabilities of its foundational architecture.
Good For
- General Language Tasks: Suitable for a wide range of applications that benefit from a Qwen3-based model.
- Developers interested in Unsloth: Provides an example of a model fine-tuned with Unsloth, showcasing its efficiency benefits.