This model is obtained through distillation training using the high-reasoning-difficulty Gemini 3 Pro preview dataset based on the Qwen3-4B-Thinking-2507 base model. It focuses on improving complex reasoning abilities in the fields of coding and science. Through training with specific datasets, it aims to efficiently transfer the reasoning abilities of large models (such as Gemini 3 Pro) to a smaller-scale model.

Natural Language ProcessingTransformers

Gemma 3n E4B IT is a lightweight multimodal open model launched by Google, built based on the same research as the Gemini model. This model supports text, audio, and visual inputs and is suitable for various tasks. It uses the MatFormer architecture to achieve efficient parameter utilization.

MultimodalTransformers

This model is a knowledge distillation model based on the Qwen3-4B architecture, trained with approximately 54.4 million tokens generated by Gemini 2.5 Flash, aiming to integrate the behavior, inference process, and knowledge of Gemini-2.5 Flash into a single dataset.

Natural Language ProcessingTransformersEnglish

Gemma 3 270M is a lightweight multimodal model launched by Google. Based on the same research technology as the Gemini series, it supports text and image input, has a 32K context window, and provides high-quality output in tasks such as question answering, summarization, image understanding, and code generation.

MultimodalTransformersMultiple Languages

Gemma 3 is a lightweight, state-of-the-art open-source model family launched by Google, built on the same research and technology as the Gemini model. This model has multimodal processing capabilities, supports text and image inputs, and generates text outputs, making it suitable for various text generation and image understanding tasks.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art open model family launched by Google, built on the same research and technology as the Gemini model. It has multi-modal processing capabilities, supports text and image inputs, and generates text outputs, suitable for various text generation and image understanding tasks.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. The 270M version is an instruction-tuned model that uses Quantization-Aware Training (QAT), which can significantly reduce memory requirements while maintaining quality similar to bfloat16.

MultimodalTransformers

Gemma 3 is a lightweight open-source multimodal model series launched by Google, built on the same technology as Gemini. The 270M version is the smallest model in the series, supporting text and image input, with a 128K context window, suitable for deployment in resource-constrained environments.

MultimodalTransformers

Gemma 3 is a lightweight open-source multimodal model family launched by Google, built on the same research technology as Gemini. The 270M version is the smallest instruction-tuned model among them, supporting over 140 languages and having a 32K context length, suitable for text generation tasks in resource-constrained environments.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. The 270M version is the smallest model among them, capable of handling text and image inputs and generating text outputs, suitable for various text generation and image understanding tasks.

MultimodalTransformers

Gemma 3 is a lightweight and state-of-the-art multimodal open model family launched by Google, built on the same research and technology as the Gemini model. This model can handle text and image inputs and generate text outputs. It has a large context window of 128K and supports over 140 languages, offering various sizes ranging from 270M to 27B.

MultimodalTransformers

Gemma 3n is a lightweight, state-of-the-art multimodal open model launched by Google, built on Gemini technology. It is designed for low-resource devices, supporting text, image, video, and audio inputs and generating text outputs. It uses selective parameter activation technology to run efficiently with a 4B parameter scale.

MultimodalTransformersEnglish

Gemma 3n-E2B-it is a lightweight open-source multimodal model launched by Google, built on the same technology as Gemini and optimized for low-resource devices.

MultimodalTransformersEnglish

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google, built on the same research and technology as the Gemini model. It supports text, audio, and visual inputs and is suitable for various tasks.

MultimodalTransformers

Gemma 3n is a lightweight and state-of-the-art open-source multimodal model family launched by Google. It is built on the same research and technology as the Gemini model and supports text, audio, and visual inputs.

MultimodalTransformers

Gemma 3 is a lightweight multimodal model launched by Google, built on the same technology as Gemini. It supports text and image input and outputs text, suitable for various tasks such as text generation and image understanding. The model comes in various sizes and can be deployed in environments with limited resources.

MultimodalTransformers

Gemma 3 is a lightweight open model series launched by Google, built on Gemini technology, supporting multimodal input and text output.

MultimodalTransformers

A 7B-parameter open-source chart understanding vision-language model developed by Bespoke Labs, outperforming closed-source models like Gemini-1.5-Pro in chart QA tasks

MultimodalSafetensorsEnglish

Gemma 3 is Google's lightweight open model series based on Gemini technology. The 12B version employs Quantization-Aware Training (QAT) technology, supports multimodal input, and features a 128K context window.

MultimodalGguf

Gemma 3 is a lightweight and state-of-the-art open model family launched by Google, built on the same research and technology as the Gemini model. This 27B version uses Quantization-Aware Training (QAT), which can significantly reduce memory requirements while maintaining quality similar to bfloat16. It has multimodal processing capabilities and a 128K large context window.

MultimodalTransformers