imleadingmylife/q-coder-br1

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 13, 2026Architecture:Transformer Featherless Exclusive Cold

The imleadingmylife/q-coder-br1 is a 3.1 billion parameter instruction-tuned language model, based on the Qwen2.5 architecture. This model was fine-tuned using Unsloth and is provided in GGUF format, optimized for efficient deployment. It is specifically designed for code-related tasks, leveraging its training for programming use cases.

Loading preview...

Overview

The imleadingmylife/q-coder-br1 is a 3.1 billion parameter language model, built upon the Qwen2.5 architecture. It has been instruction-tuned and converted to the GGUF format, making it suitable for local deployment and efficient inference. The fine-tuning process utilized Unsloth, which is noted for its speed in training.

Key Capabilities

  • Code-centric tasks: The model is specifically designed and fine-tuned for applications involving code.
  • GGUF Format: Provided in GGUF format, ensuring compatibility with various inference engines like llama-cli and ollama.
  • Efficient Training: Benefits from Unsloth's accelerated training methods.

Deployment and Usage

This model can be easily deployed using tools like llama-cli for text-only interactions or llama-mtmd-cli for multimodal models, with Jinja templating support. An Ollama Modelfile is also included, simplifying deployment within the Ollama ecosystem. The primary available file is qwen2.5-coder-3b-instruct.Q4_K_M.gguf.