Ai2 OLMoE
Ai2 OLMoE is a fully open source mixture-of-experts language model that is capable of running completely on-device, allowing you to try our model privately and securely. Our app is intended to help researchers better explore how to make on-device intelligence better and to enable developers to quickly prototype new AI experiences, all with no cloud connectivity required. OLMoE is a highly efficient mixture-of-experts version of the Ai2 OLMo family of models. Experience which real-world tasks state-of-the-art local models are capable of. Research how to improve small AI models. Test your own models locally using our open-source codebase. Integrate OLMoE into other iOS applications. The Ai2 OLMoE app provides privacy and security by operating completely on-device. Easily share the output of your conversations with friends or colleagues. The OLMoE model and the application code are fully open source.
Learn more
GPT-5.2 Thinking
GPT-5.2 Thinking is the highest-capability configuration in OpenAI’s GPT-5.2 model family, engineered for deep, expert-level reasoning, complex task execution, and advanced problem solving across long contexts and professional domains. Built on the foundational GPT-5.2 architecture with improvements in grounding, stability, and reasoning quality, this variant applies more compute and reasoning effort to generate responses that are more accurate, structured, and contextually rich when handling highly intricate workflows, multi-step analysis, and domain-specific challenges. GPT-5.2 Thinking excels at tasks that require sustained logical coherence, such as detailed research synthesis, advanced coding and debugging, complex data interpretation, strategic planning, and sophisticated technical writing, and it outperforms lighter variants on benchmarks that test professional skills and deep comprehension.
Learn more
Qwen3.6-Max-Preview
Qwen3.6-Max-Preview is a next-generation frontier language model designed to push the limits of intelligence, instruction following, and real-world agent capabilities within the Qwen ecosystem. Building on the Qwen3 series, this preview release introduces stronger world knowledge, sharper instruction alignment, and significant improvements in agentic coding performance, enabling the model to better handle complex, multi-step tasks and software engineering workflows. It is engineered for advanced reasoning and execution scenarios, where the model not only generates responses but also interacts with tools, processes long contexts, and supports structured problem-solving across domains such as coding, research, and enterprise workflows. The architecture continues the Qwen focus on large-scale, high-efficiency models capable of handling extensive context windows and delivering consistent performance across multilingual and knowledge-intensive tasks.
Learn more
Ring 2.6
Ring is a trillion-parameter thinking model from Ant Group, designed for real-world Agent workflows. It uses the same Mixture of Experts architecture as Ling, activating about 63B parameters per inference, and focuses on coding agents, tool use, multi-tool collaboration, engineering development, research analysis, and long-horizon task execution. Rather than only pursuing “smarter” results, Ring is built to consistently complete complex tasks at reasonable cost, balancing quality, speed, and execution efficiency in production environments. Ring-2.6-1T introduces an adjustable Reasoning Effort mechanism with high and xhigh reasoning intensity levels, using adaptive reasoning budget allocation based on task complexity. High mode is designed for high-frequency Agent workflows, lower token cost, faster multi-step execution, multi-turn interaction, tool collaboration, and task decomposition.
Learn more