pankajmathur/Mimma-3-12b
VISIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kLicense:gemmaArchitecture:Transformer0.0K Cold

Mimma-3-12b by pankajmathur is a multimodal vision-language model based on the Gemma 3 architecture, designed to handle both text and image inputs and generate text outputs. This 12 billion parameter model features a large 128K context window and multilingual support for over 140 languages. It excels at a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, making it suitable for resource-limited environments.

Loading preview...