jtamondo/chonky
VISIONPricing:Input $1.06 / Cached $0.15 / Output $2.6Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 28, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The jtamondo/chonky model is a 27 billion parameter Qwen3.5-based causal language model, fine-tuned by jtamondo. It was trained using Unsloth and Huggingface's TRL library, enabling faster training. This model is designed for general language generation tasks, leveraging its large parameter count and efficient training methodology.
Loading preview...
jtamondo/chonky: A Fine-Tuned Qwen3.5 Model
The jtamondo/chonky model is a 27 billion parameter language model based on the Qwen3.5 architecture. It has been fine-tuned by jtamondo, leveraging the Unsloth library for accelerated training, achieving a 2x speed improvement, in conjunction with Huggingface's TRL library.
Key Capabilities
- Qwen3.5 Architecture: Built upon the robust Qwen3.5 foundation, providing strong general language understanding and generation capabilities.
- Efficient Training: Utilizes Unsloth for significantly faster fine-tuning, making it a potentially more accessible and rapidly deployable model.
- Large Parameter Count: With 27 billion parameters, it offers substantial capacity for complex tasks and nuanced responses.
Good For
- General Language Generation: Suitable for a wide range of text generation tasks, including content creation, summarization, and conversational AI.
- Experimentation with Efficient Fine-tuning: Developers interested in models trained with Unsloth for speed and resource optimization.
- Applications requiring a large, capable language model: Where the Qwen3.5 base architecture and 27B parameters are beneficial.