⌘KCtrl+K
A state-of-the-art general purpose MoE VLM ideal for chat, agentic and instruction based use cases.
Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.
Latency-optimized language model excelling in code, math, general knowledge, and instruction-following.
Built for agentic workflows, this model excels in coding, instruction following, and function calling
This LLM follows instructions, completes requests, and generates creative text.
The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.
This LLM follows instructions, completes requests, and generates creative text.
Efficient multimodal model excelling at multilingual tasks, image understanding, and fast-responses
GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation.