kyoungsook70/dama-aibrain

VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:5.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 21, 2026Architecture:Transformer Featherless Exclusive Cold

The kyoungsook70/dama-aibrain is a 5.1 billion parameter model, fine-tuned and converted to GGUF format using Unsloth. This model includes both text-only and multimodal (vision-capable) variants, with a context length of 32768 tokens. It is optimized for efficient deployment and use in local inference environments, particularly for applications requiring multimodal understanding.

Loading preview...

dama-aibrain: Efficient GGUF Model for Text and Multimodal Tasks

The kyoungsook70/dama-aibrain model is a 5.1 billion parameter language model, specifically fine-tuned and converted into the GGUF format using the Unsloth framework. This optimization allows for faster training and efficient deployment on various hardware.

Key Capabilities & Features

  • GGUF Format: Provided in GGUF format, making it suitable for local inference with tools like llama-cli and ollama.
  • Multimodal Support: Includes a vision-capable variant (gemma-4-e2b-it.BF16-mmproj.gguf) alongside a text-only version (gemma-4-e2b-it.Q8_0.gguf).
  • Optimized with Unsloth: Benefits from Unsloth's efficiency, enabling 2x faster training.
  • Ollama Compatibility: Instructions are provided for creating a unified model for Ollama, addressing its current limitation with separate mmproj files for vision models.

Use Cases

  • Local Inference: Ideal for developers looking to run LLMs and multimodal models locally.
  • Multimodal Applications: Suitable for tasks requiring both text and image understanding.
  • Efficient Deployment: Designed for environments where resource efficiency and fast inference are critical.