Qwen3-Coder-REAP-363B-A35B is a sparse mixture-of-experts model obtained by pruning 25% of the experts from Qwen3-Coder-480B-A35B-Instruct using the REAP method. While maintaining performance close to the original model, it significantly reduces the parameter scale and memory requirements, making it particularly suitable for code generation and intelligent coding scenarios with limited resources.

Natural Language ProcessingTransformersEnglish

MiniMax-M2 is a small Mixture of Experts (MoE) model built specifically for maximizing coding and agent workflows. It has a total of 230 billion parameters, with 1 billion active parameters. This model excels in coding and agent tasks while maintaining strong general intelligence. It is compact, fast, and cost-effective.

Natural Language ProcessingTransformers

JanusCoder-14B is an open-source foundation model with 14B parameters built on Qwen3-14B, aiming to establish a unified visual programming interface for code intelligence. This model is trained on the JANUSCODE-800K multimodal code corpus and can handle various visual programming tasks in a unified manner.

Natural Language ProcessingTransformers

JanusCoder-8B is an open-source code intelligence foundation model built on Qwen3-8B, aiming to establish a unified visual programming interface. This model is trained on JANUSCODE-800K (the largest multimodal code corpus to date) and can handle various visual programming tasks, including data visualization, interactive web UI, and code-driven animation.

MultimodalTransformers

Emu3.5 is a native multimodal model developed by the Beijing Academy of Artificial Intelligence (BAAI). It can jointly predict the next state across vision and language, enabling coherent world modeling and generation. After end-to-end pre-training and large-scale reinforcement learning post-training, it demonstrates excellent performance in multimodal tasks.

MultimodalTransformers

Emu3.5 is a native multimodal model developed by the Beijing Academy of Artificial Intelligence (BAAI). It can jointly predict the next state across vision and language, achieving coherent world modeling and generation, and performs excellently in multimodal tasks.

MultimodalTransformers

Qwen3-VL is the most powerful vision-language model in the Tongyi large model series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning capabilities, long context support, strong spatial and video dynamic understanding capabilities, and outstanding intelligent agent interaction capabilities. This model uses a Mixture of Experts (MoE) architecture and is a thinking version for enhanced reasoning.

MultimodalGguf

Qwen3 - VL is the most powerful vision - language model in the Tongyi series. It has excellent text understanding and generation capabilities, in - depth visual perception and reasoning abilities, long - context support, strong spatial and video dynamic understanding abilities, and outstanding intelligent agent interaction abilities.

MultimodalTransformers

Scout is a professional language model fine-tuned by VANTA Research based on the Google Gemma 3 4B Instruct architecture. It excels in constraint-aware reasoning and adaptive problem solving, and is擅长侦察式情报收集 should be translated as is good at scouting-style intelligence gathering。擅长侦察式情报收集、系统问题分解和自适应解决方案生成。It is good at scouting-style intelligence gathering, system problem decomposition, and adaptive solution generation.

Natural Language ProcessingTransformersEnglish

MiniMax-M2 is a small Mixture of Experts (MoE) model built specifically for maximizing coding and agent workflows. It has a total of 230 billion parameters, with only 10 billion parameters activated. It performs excellently in coding and agent tasks while maintaining strong general intelligence, featuring compactness, speed, and cost-effectiveness.

Natural Language ProcessingTransformers

MiniMax-M2 is a 'mini' model built specifically for maximizing coding and agent workflows. It is a compact, fast, and cost-effective Mixture of Experts (MoE) model that excels in coding and agent tasks while also possessing strong general intelligence.

Natural Language ProcessingTransformers

Wraith-8B is the first model in the VANTA Research entity series, fine-tuned based on Meta's Llama 3.1 8B Instruct. This model performs excellently in mathematical reasoning, achieving an accuracy rate of 70% in the GSM8K benchmark test. It also has a unique cosmic intelligence perspective, providing strong support for various application scenarios.

Natural Language ProcessingTransformersEnglish

Nanonets-OCR2-1.5B-exp GGUF is a powerful image-to-markdown OCR model that can convert documents into a structured markdown format and perform intelligent content recognition and semantic tagging. It supports the processing of multi-language documents.

MultimodalTransformersOther

AesCoder-4B is a large language model focused on improving the aesthetic quality of code. It optimizes the aesthetic performance of code generation through an intelligent reward feedback mechanism and performs well in visual coding tasks such as web design and game development.

Natural Language ProcessingTransformers

This is the latest cutting-edge model in the field of accuracy, dedicated to achieving artificial grain intelligence, and has made significant progress with the assistance of the world's top grain planting teams. This model is based on the Qwen3-0.6B architecture and is fully fine-tuned locally using an RX 9070 XT graphics card and the unsloth tool.

Natural Language ProcessingSafetensorsEnglish

KaniTTS is a high-speed, high-fidelity Arabic text-to-speech model optimized for real-time conversational artificial intelligence applications. It adopts a two-stage pipeline architecture, combining a large language model with an efficient audio codec to achieve excellent speed and audio quality, and can meet the speech synthesis needs of multiple fields such as conversational AI, accessibility assistance, and research.

Audio ProcessingTransformersArabic

The Nanonets-OCR2-3B GGUF model is a powerful tool designed for document processing. It can intelligently convert various types of documents into structured Markdown format and has multiple advanced recognition and processing capabilities such as OCR, image-to-text conversion, PDF-to-Markdown conversion, and visual question answering.

MultimodalTransformersOther

MiniMax-M2 is a 'mini' model specifically built to maximize coding and agent workflows. It adopts a Mixture of Experts architecture, with a total of 230 billion parameters and 10 billion active parameters. This model excels in coding and agent tasks while maintaining strong general intelligence. It is compact, fast, and cost-effective.

Natural Language ProcessingTransformers

NVIDIA Nemotron Nano v2 12B VL is a powerful multimodal vision-language model that supports multi-image reasoning and video understanding, and has document intelligence, visual question answering, and summarization capabilities. It can be used for commercial purposes.

MultimodalTransformers

PokeeResearch-7B is a 7-billion-parameter deep research intelligent agent developed by Pokee AI. It combines reinforcement learning based on AI feedback (RLAIF) with an inference framework and can execute complex multi-step research workflows, including self-correction, verification, and comprehensive analysis.

Natural Language ProcessingTransformersEnglish