enesozdemr/gemma-3-finetune

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kPublished:Jul 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The enesozdemr/gemma-3-finetune is a 1 billion parameter language model, fine-tuned from unsloth/gemma-3-1b-it-unsloth-bnb-4bit. Developed by enesozdemr, this model is specifically optimized for performance on Turkish language tasks, as indicated by its benchmark results on Turkish MMLU. It achieves a 43.02% success rate on a 6200-question Turkish MMLU benchmark, making it suitable for applications requiring Turkish language understanding and generation.

Loading preview...

Overview

The enesozdemr/gemma-3-finetune is a 1 billion parameter language model, developed by enesozdemr. It is a fine-tuned version of the unsloth/gemma-3-1b-it-unsloth-bnb-4bit model, designed to enhance its capabilities, particularly for Turkish language processing.

Key Capabilities

  • Turkish Language Proficiency: The model demonstrates a notable focus on the Turkish language, as evidenced by its benchmark results on the Turkish MMLU dataset.
  • Benchmark Performance: It achieved a 43.02% success rate on a Turkish MMLU benchmark consisting of 6200 questions, correctly answering 2667 questions. The evaluation took approximately 2.65 hours (9560 seconds).
  • Compact Size: With 1 billion parameters, it offers a relatively efficient footprint for deployment while still providing specialized language capabilities.

Good For

  • Applications requiring Turkish language understanding and generation.
  • Developers looking for a fine-tuned Gemma 1B variant with improved performance on Turkish-specific tasks.
  • Use cases where resource efficiency is important, given its 1B parameter size.