OpenThinker - Agent - v1 is an open - source intelligent agent model that is subsequently trained based on Qwen3 - 8B. It is designed for terminal operations and software engineering tasks. It is first trained on a high - quality supervised fine - tuning dataset and then further optimized through reinforcement learning. It performs excellently in agent benchmark tests such as Terminal - Bench 2.0 and SWE - Bench.

Natural Language ProcessingTransformersOther

Fyodor-Q3-8B-Instruct is a high-fidelity instruction-tuned model designed for intelligent reasoning and robust code generation. It is based on the Qwen3-8B architecture and trained with a high-rank LoRA configuration. It excels in planning before coding and is well-suited for complex software engineering tasks.

Natural Language ProcessingTransformersMultiple Languages

Qwen3-32B is the latest generation of large language models in the Qwen series, with powerful reasoning, instruction-following, intelligent agent interaction, and multilingual processing capabilities. It supports over 100 languages and dialects and can seamlessly switch between thinking and non-thinking modes, providing users with a natural and smooth dialogue experience.

Natural Language ProcessingTransformers

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

Qwen3-VL-4B-Instruct is the latest vision-language model in the Tongyi Qianwen series. It achieves excellent visual perception, text understanding and generation, spatial reasoning, and intelligent agent interaction capabilities at the 4B parameter scale. It supports long contexts and video understanding, and has powerful OCR and multi-language processing capabilities.

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

Qwen3-VL-2B-Thinking is the most powerful vision-language model in the Qwen series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, enhanced spatial and video dynamic understanding abilities, and stronger intelligent agent interaction capabilities. This model uses a 2B parameter scale and supports the instruction version and the thinking version with enhanced reasoning.

MultimodalTransformers

This is a pre-trained language model that merges Vistral-24B-Instruct and Cydonia-24B-v4.2.0 using the SLERP method, specifically optimized to support bilingual processing capabilities in Russian and English. The model intelligently combines the advantages of the two base models, enhancing English performance while maintaining Russian capabilities.

Natural Language ProcessingTransformersMultiple Languages

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

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

NanoAgent is a compact large intelligent language model with 135 million parameters and an 8k context length. It is specifically optimized for tool calls and instruction following, and can run efficiently on personal devices, supporting lightweight inference and ReAct-style interactions.

Natural Language ProcessingMlxEnglish

Tongyi Deep Research 30B is a large language model with 30 billion parameters, designed specifically for long-cycle, deep information search tasks. This model performs excellently in multiple intelligent search benchmark tests, uses innovative quantization methods to improve performance, and supports intelligent pre-training, supervised fine-tuning, and reinforcement learning.

Natural Language ProcessingTransformersEnglish

Qwen3-VL is the most powerful vision-language model in the Qwen 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 version uses a mixture-of-experts model architecture and supports enhanced reasoning thinking functions.

MultimodalSafetensors

The Dorado Network Surfing Tool Extended Version is a function call and intelligent reasoning model fine-tuned based on Tongyi Qianwen 3 - 4B. It is designed for network search orchestration, tool-enhanced reasoning, and dynamic problem solving. It excels in intelligent decision-making, tool selection, and structured execution processes.

Natural Language ProcessingTransformersEnglish

zen-agent-4b is an intelligent agent for tool invocation with 4 billion parameters, supporting the Model Context Protocol (MCP), which provides strong assistance for text generation tasks. This model is developed by Zen Research DAO, affiliated with the non - profit organization Zoo Labs Inc.

Natural Language ProcessingTransformersEnglish

Fathom-DeepResearch is an intelligent deep research system composed of two specialized 4B parameter models: Fathom-Search-4B is optimized for long-term evidence search, and Fathom-Synthesizer-4B is used for open-ended synthesis and report generation. This system has achieved state-of-the-art performance in multiple search-intensive benchmark tests and has outperformed multiple closed-source deep research agents on the open-ended synthesis benchmark.

Natural Language ProcessingTransformers

This is a professional quantized version of the Qwen3-Omni model with 31.7B parameters. It uses advanced INT8+FP16 mixed-precision quantization technology, reducing memory usage by over 50%. It supports intelligent GPU/CPU hybrid inference, enabling large multimodal models to run efficiently on consumer-grade hardware.

MultimodalSafetensorsMultiple Languages

This is the GGUF quantized version of Alibaba's Qwen series large language model with 8 billion parameters, designed for advanced reasoning, intelligent agent behavior, and multilingual tasks, and can be used with llama.cpp and compatible tools.

Natural Language ProcessingGgufMultiple Languages