Step 3.5 Flash
Step 3.5 Flash is an advanced open source foundation language model engineered for frontier reasoning and agentic capabilities with exceptional efficiency, built on a sparse Mixture of Experts (MoE) architecture that selectively activates only about 11 billion of its ~196 billion parameters per token to deliver high-density intelligence and real-time responsiveness. Its 3-way Multi-Token Prediction (MTP-3) enables generation throughput in the hundreds of tokens per second for complex multi-step reasoning chains and task execution, and it supports efficient long contexts with a hybrid sliding window attention approach that reduces computational overhead across large datasets or codebases. It demonstrates robust performance on benchmarks for reasoning, coding, and agentic tasks, rivaling or exceeding many larger proprietary models, and includes a scalable reinforcement learning framework for consistent self-improvement.
Learn more
MiMo-V2-Omni
MiMo-V2-Omni is an advanced multimodal AI model designed to handle a wide range of real-world tasks across text, code, and other data formats. It is built to support agentic workflows, enabling seamless execution of complex, multi-step processes. The model integrates strong reasoning, tool usage, and contextual understanding to deliver reliable outputs. With its ability to process diverse inputs, it enhances productivity across development, automation, and enterprise use cases. MiMo-V2-Omni focuses on delivering consistent performance in both general and specialized tasks.
Learn more
Nemotron 3 Ultra
Nemotron 3 Nano is a compact, open large language model in NVIDIA’s Nemotron 3 family, designed for efficient agentic reasoning, conversational AI, and coding tasks. It uses a hybrid Mixture-of-Experts Mamba-Transformer architecture that activates only a small subset of parameters per token, enabling low-latency inference while maintaining strong accuracy and reasoning performance. It has approximately 31.6 billion total parameters with around 3.2 billion active (3.6 billion including embeddings), allowing it to achieve higher accuracy than previous Nemotron 2 Nano while using less computation per forward pass. Nemotron 3 Nano supports long-context processing of up to one million tokens, enabling it to handle large documents, multi-step workflows, and extended reasoning chains in a single pass. It is designed for high-throughput, real-time execution, excelling in multi-turn conversations, tool calling, and agent-based workflows where tasks require planning, reasoning, and more.
Learn more
MiMo-V2-Pro
Xiaomi MiMo-V2-Pro is a flagship AI foundation model designed to power real-world agentic workflows and complex task execution. It is built to function as the core intelligence behind agent systems, enabling orchestration of multi-step processes and production-level tasks. The model demonstrates strong capabilities in coding, tool usage, and search-based tasks, performing competitively on global benchmarks. With its large-scale architecture and extended context window, it can handle long and complex interactions efficiently. MiMo-V2-Pro is optimized for practical applications, delivering reliable performance across development, automation, and enterprise workflows.
Learn more
