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

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-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

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

Fathom-DeepResearch is a dual-model intelligent system composed of Fathom-Search-4B and Fathom-Synthesizer-4B. It is optimized for long-term network search, evidence verification, and generating reports rich in references. This system achieves the optimal performance of open-source weights in search-intensive tasks, surpassing multiple closed-source deep research agents.

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

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 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

This is the GGUF quantized version of the Qwen/Qwen3-4B language model, a large language model with 4 billion parameters developed by Alibaba's Tongyi series. It is designed for consumer-grade hardware and supports powerful reasoning, intelligent agent workflows, and multilingual interaction.

Natural Language ProcessingGgufMultiple Languages

DeepSeek-V3.1 is a large language model that is post-trained based on DeepSeek-V3.1-Base. It has a 128K context length and supports mixed thinking modes, intelligent tool invocation, and code proxy functions. This model performs excellently in multiple benchmark tests, especially showing significant improvements in mathematical reasoning, code generation, and search agent tasks.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-Air-AWQ is an 8-bit quantized version based on the GLM-4.5-Air base model, designed specifically for intelligent agents. It uses a hybrid reasoning mode, supports complex reasoning and instant response, and is released under the MIT open-source license.

Natural Language ProcessingTransformersMultiple Languages

NexaAI/Qwen3-4B is a large language model with 4 billion parameters based on the Qwen3 series. It supports seamless switching between thinking mode and non-thinking mode and performs excellently in reasoning, instruction following, intelligent agent capabilities, and multilingual support.

Natural Language ProcessingGguf

GLM-4.5 is a foundation model designed for intelligent agents, integrating inference, coding, and intelligent agent capabilities. It has a total of 355 billion parameters and ranks 3rd in 12 industry-standard benchmark evaluations, scoring 63.2. It uses the MIT open-source license and can be used for commercial purposes and secondary development.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-AWQ is a 4-bit quantized version based on the GLM-4.5 base model. It uses the advanced AWQ quantization method, significantly improving inference efficiency while maintaining good performance. This model is specifically designed for intelligent agents, integrating reasoning, encoding, and intelligent agent capabilities.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-Air-AWQ is a quantized version of the GLM-4.5-Air model. It improves inference efficiency through AWQ quantization technology while maintaining high performance. This model has 10.6 billion parameters, of which 1.2 billion are active parameters. It is specially designed for intelligent agents and supports both complex reasoning and instant response modes.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-Air-AWQ is a text generation model that performs 4-bit AWQ quantization based on the zai-org/GLM-4.5-Air base model. It is specifically designed for intelligent agent applications and performs excellently in reasoning, coding, and intelligent agent capabilities. It uses the MIT open-source license.

Natural Language ProcessingTransformersMultiple Languages