lishoo/qwen3-project-planner
TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 27, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The lishoo/qwen3-project-planner is an 8 billion parameter Qwen3 model, developed by lishoo, and finetuned from unsloth/qwen3-8b-unsloth-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 its Qwen3 architecture and efficient training methodology.
Loading preview...
Model Overview
The lishoo/qwen3-project-planner is an 8 billion parameter language model, finetuned by lishoo. It is based on the Qwen3 architecture, specifically finetuned from the unsloth/qwen3-8b-unsloth-bnb-4bit model.
Key Capabilities
- Efficient Training: This model was trained significantly faster (2x speedup) by utilizing Unsloth and Huggingface's TRL library. This indicates an optimization in the training process, potentially leading to more accessible and quicker iterations for similar models.
- Qwen3 Architecture: Leveraging the Qwen3 base, it inherits the general language understanding and generation capabilities of this family of models.
Good For
- General Language Tasks: Suitable for a broad range of applications requiring text generation, comprehension, and conversational abilities.
- Developers Interested in Efficient Finetuning: The model serves as an example of successful and accelerated finetuning using Unsloth, which can be a valuable reference for developers looking to optimize their own training workflows.