ianpaqt/gemma-3-sql
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Aug 28, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The ianpaqt/gemma-3-sql is a 0.3 billion parameter language model developed by ianpaqt, fine-tuned from unsloth/gemma-3-270m-it. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. With a context length of 32768 tokens, it is optimized for SQL-related tasks, leveraging its efficient training for specialized applications.
Loading preview...
ianpaqt/gemma-3-sql: Efficiently Fine-Tuned for SQL
The ianpaqt/gemma-3-sql is a compact yet powerful 0.3 billion parameter language model, specifically fine-tuned for SQL-related applications. Developed by ianpaqt, this model builds upon the unsloth/gemma-3-270m-it base.
Key Capabilities
- SQL Task Optimization: Designed to excel in tasks involving SQL, making it suitable for database interactions, query generation, or analysis.
- Efficient Training: Leverages Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- Compact Size: At 0.3 billion parameters, it offers a balance between performance and resource efficiency.
- Extended Context Window: Features a substantial context length of 32768 tokens, allowing it to process longer and more complex SQL queries or related data.
Good for
- SQL Query Generation: Automating the creation of SQL queries from natural language or other inputs.
- Database Interaction: Applications requiring intelligent parsing or manipulation of SQL statements.
- Resource-Constrained Environments: Its smaller size makes it suitable for deployment where computational resources are limited.
- Rapid Prototyping: The efficient training process allows for quicker iteration and development of SQL-focused AI solutions.