quangvu197/Gemma_3_1b_GRPO

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kPublished:Aug 14, 2026Architecture:Transformer Featherless Exclusive Cold

quangvu197/Gemma_3_1b_GRPO is a 1 billion parameter Gemma-based language model, fine-tuned and converted to GGUF format using Unsloth. This model is optimized for efficient deployment and inference on local hardware, providing readily available quantized versions. It is primarily designed for general text generation tasks where a compact and performant model is required.

Loading preview...

Model Overview

quangvu197/Gemma_3_1b_GRPO is a 1 billion parameter Gemma-based language model that has been fine-tuned and converted into the GGUF format. This conversion and optimization process was performed using Unsloth, which is noted for its speed improvements in training.

Key Features

  • GGUF Format: The model is provided in GGUF format, making it compatible with llama.cpp and related tools for efficient local inference.
  • Quantized Versions: Several quantized versions are available, including Q5_K_M, Q8_0, and Q4_K_M, allowing users to choose based on their performance and memory requirements.
  • Ollama Support: An Ollama Modelfile is included, simplifying deployment and usage within the Ollama ecosystem.
  • Optimized Training: The fine-tuning process leveraged Unsloth, which reportedly offers 2x faster training.

Use Cases

This model is suitable for developers looking for a compact and efficient Gemma-based model for:

  • Local inference on consumer hardware.
  • Applications requiring a small footprint language model.
  • Experimentation with Gemma architecture in a GGUF environment.

Finetunes
2 models