AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: LLM
81 article(s) found · Clear tag
Wan-Streamer v0.2 – A Full-Modal Understanding and Generation Model from Alibaba Tongyi
Wan-Streamer v0.2 is an end-to-end full-modal understanding and generation model introduced by Alibaba Tongyi Lab, designed for real-time full-duplex interaction. This model processes real-time unders...
Qwen3.8-Max-Preview – The Latest Base Model from Tongyi Qianwen
Qwen3.8-Max-Preview is the preview version of the latest generation of base large models introduced by the Tongyi Qianwen team. With a parameter count as high as 2.4T, it employs a Mixture of Experts ...
Nemotron-Labs-Diffusion – NVIDIA's Open-Source Three-Mode Language Model
Nemotron-Labs-Diffusion is a series of three-mode language models launched by NVIDIA, unifying autoregressive (AR), diffusion, and self-speculative decoding within a single architecture. Through joint...
VibeThinker-3B – Weibo's Open-Source 3-Billion-Parameter Dense Reasoning Model
VibeThinker-3B is a 3-billion-parameter dense reasoning model open-sourced by the AI team at Weibo. Built upon the Qwen2.5-Coder-3B base model, it undergoes an enhanced Spectrum-to-Signal post-trainin...
Hy3 – Tencent Hunyuan's Open-Source Mixture of Experts Model
Hy3 is a 295B-parameter Mixture of Experts (MoE) model open-sourced by the Tencent Hunyuan team. It demonstrates significant improvements in agent capabilities, reasoning, and long-context tasks, with...
Elements Claw – Alibaba DAMO Academy's AI Agent for Superconducting Material Discovery
Elements Claw is the industry's first AI agent for superconducting material discovery, jointly launched by Alibaba DAMO Academy, Renmin University of China, and the University of Chinese Academy of Sc...
DSpark – Speculative Decoding Acceleration Framework Open-Sourced by DeepSeek and Peking University
DSpark is a speculative decoding acceleration framework jointly open-sourced by DeepSeek and Peking University, designed to address the core pain point of slow, "toothpaste-like" autoregressive genera...
Sakana Fugu – A Multi-Agent Orchestration System by Sakana AI
Sakana Fugu is a multi-agent orchestration system developed by Sakana AI, which dynamically schedules top-tier models through a single API to achieve emergent collective intelligence. The system features a built-in TRINITY evolutionary coordinator and a Conductor reinforcement learning orchestrator, automatically assigning roles such as thinker, executor, and verifier to different models without the need for manual workflow presets. Fugu supports recursive self-invocation and flexible model pool management, offering both Standard and Ultra editions. It achieves cutting-edge performance in rigorous benchmark tests, rivaling Fable 5 and Mythos Preview,...
MMSkills – A Multimodal Skill Framework Jointly Launched by Shanghai Jiao Tong University and Xiaohongshu
MMSkills is a multimodal skill framework jointly developed by Shanghai Jiao Tong University and Xiaohongshu, specifically designed for general-purpose visual agents. This framework extends traditional...
SkillOpt – Microsoft's Open-Source Agent Skill Documentation Optimization Tool
SkillOpt is an open-source Agent skill documentation optimization tool developed by Microsoft. Its core concept is introducing the deep learning training paradigm into the text space, treating the Age...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.