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-cliandollama. - 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
mmprojfiles 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.