electroglyph/ternary-bonsai-8b-sft-bf16-11

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 30, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The electroglyph/ternary-bonsai-8b-sft-bf16-11 is an 8 billion parameter Qwen3 model, fine-tuned from prism-ml/Ternary-Bonsai-8B-unpacked. Developed by electroglyph, this model was trained using Unsloth, enabling a 2x faster training process. It is designed for general language tasks, leveraging its Qwen3 architecture and efficient training methodology.

Loading preview...

Model Overview

The electroglyph/ternary-bonsai-8b-sft-bf16-11 is an 8 billion parameter language model developed by electroglyph. It is fine-tuned from the prism-ml/Ternary-Bonsai-8B-unpacked base model, utilizing the Qwen3 architecture.

Key Characteristics

  • Architecture: Based on the Qwen3 model family.
  • Parameter Count: Features 8 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: This model was trained with Unsloth, which facilitated a 2x faster training process compared to standard methods.
  • Context Length: Supports a context length of 32768 tokens, suitable for processing longer inputs and generating coherent, extended responses.

Use Cases

This model is suitable for a variety of general-purpose language understanding and generation tasks, benefiting from its efficient training and substantial parameter count. Its Qwen3 foundation suggests capabilities across areas like text summarization, question answering, and content creation.