AWS continues to expand access to the most advanced foundation models with OpenAI open weight models now available in Amazon Bedrock and Amazon SageMaker JumpStart. Accessing these new models from OpenAI on AWS, gpt-oss-120b and gpt-oss-20b, gives you more freedom to innovate and choose the right model for your specific use cases while maintaining complete control over your infrastructure and data.

Last week, the OpenSearch and Valkey teams visited Seoul to meet open source developers and contributors in the Open Source Summit Korea 2026 and MCP DevSummit Seoul 2026. At the four-day event, community leaders and users of open source projects and emerging agent AI gathered to share knowledge, collaborate on solutions, and push the projects […]

AWS continues to expand access to the most advanced foundation models with OpenAI open weight models now available in Amazon Bedrock and Amazon SageMaker JumpStart. Accessing these new models from OpenAI on AWS, gpt-oss-120b and gpt-oss-20b, gives you more freedom to innovate and choose the right model for your specific use cases while maintaining complete control over your infrastructure and data.

NVIDIA's LocateAnything-3B, Qwen's Qwen-AgentWorld-35B-A3B, and Qwen's Qwen3.5-122B-A10B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning visual grounding, agent environment simulation, and large-scale multimodal reasoning, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: LocateAnything-3B is optimized for fast, high-quality visual grounding and object localization from natural language instructions. It uses a Parallel Box Decoding (PBD) framework that decodes bounding boxes and points as atomic units in a single step, preserving geometric coherence and unlocking substantial parallelism. It enables precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI applications. Qwen-AgentWorld-35B-A3B excels in simulating agent environments across seven interaction domains: tool calling, search, terminal, software engineering, Android, web, and OS interaction. It is the first language world model to cover all seven domains within a single model, predicting next environment states given an agent's action and interaction history via long chain-of-thought reasoning—trained on over 10 million real-world interaction trajectories. Qwen3.5-122B-A10B provides high-performance multimodal reasoning with production-friendly efficiency. It features 122B total parameters with only 10B activated per token through a hybrid architecture integrating Gated Delta Networks with sparse Mixture-of-Experts (256 experts), delivering strong reasoning, coding, agents, and visual understanding performance with a native 262K context window and minimal latency overhead. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

MiniMax-M2 is now available on Amazon SageMaker JumpStart, providing customers with immediate access to deploy this efficient open-source model in minutes. With SageMaker JumpStart, you can quickly discover, evaluate, and deploy MiniMax-M2 using either SageMaker Studio's intuitive interface or the SageMaker Python SDK for programmatic deployment. MiniMax-M2 redefines efficiency for agents. It's a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence. To learn more about deploying foundation models with SageMaker JumpStart, deployment options with the SDK, and best practices for implementation, refer to our documentation. MiniMax-M2 is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Tokyo), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Mumbai), Asia Pacific (Sydney), Asia Pacific (Jakarta), Canada (Central), Europe (Frankfurt), Europe (Stockholm), Europe (Ireland), Europe (London), Europe (Paris), South America (São Paulo).

Today, AWS announced the availability of all-MiniLM-L12-v2 in Amazon SageMaker JumpStart, expanding the portfolio of models available to AWS customers. This model from Sentence Transformers maps sentences and paragraphs to a 384-dimensional dense vector space, enabling customers to build high-quality semantic search, text clustering, and sentence similarity applications on AWS infrastructure. all-MiniLM-L12-v2 excels at encoding sentences and short paragraphs into dense vector representations that capture semantic meaning, making it ideal for information retrieval, semantic search systems, document clustering, duplicate detection, and paraphrase identification. Its compact architecture delivers fast inference while maintaining strong embedding quality, well suited for production workloads that require efficient text representations at scale. With SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio or use the SageMaker Python SDK to deploy the model to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Meta's Muse-Glimmer-30B and Alibaba's Qwen 3.8-27B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning autonomous local agentic workflows and multimodal long-horizon reasoning, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Muse-Glimmer-30B is engineered for autonomous agentic tasks with multi-step reasoning, tool use, and failure recovery. This 30B-parameter dense model from Meta Superintelligence Lab combines a dedicated ~1.8B ViT-G/14 perception encoder with interleaved text and image inputs, a 131K+ context window, and selectable reasoning strength (low through extra-high). Released under Apache 2.0, it handles sequential tool calls, recovers from failures, and operates entirely without cloud infrastructure which is ideal for always-on enterprise agents. Qwen 3.8-27B excels in coding, multi-step agentic tasks, and multimodal understanding across text, images, and video. A dense 27B-parameter native vision-language model with a 262K context window (extendable to ~1M via YaRN scaling), it delivers substantial gains over its predecessor with adjustable reasoning effort levels. Scoring 61.7 on SWE-bench Pro and running at ~17GB quantized, it carries complex multi-step tasks through to completion with greater reliability. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Today, AWS announced the availability of Qwen3-Coder-Next, Qwen3-30B-A3B, Qwen3-30B-A3B-Thinking-2507, Qwen3-Coder-30B-A3B-Instruct, and Qwen3.5-4B in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These five models from Qwen bring specialized capabilities spanning agentic coding, efficient reasoning, extended thinking, and multimodal understanding, enabling customers to build sophisticated AI applications across diverse use cases on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Qwen3-Coder-Next excels at long-horizon reasoning, complex tool use, and recovery from execution failures, making it ideal for powering coding agents in CLI/IDE platforms. Qwen3-30B-A3B uniquely supports seamless switching between thinking and non-thinking modes, making it well suited for general-purpose assistant tasks like multilingual dialogue, math reasoning, and tool calling. Qwen3-30B-A3B-Thinking-2507 delivers significantly improved performance on complex reasoning tasks in math, science, and coding, with enhanced long-context understanding. Qwen3-Coder-30B-A3B-Instruct is designed for agentic coding workflows with a custom function call format and repo-scale context understanding. Qwen3.5-4B supports unified vision-language training and  201 languages, making it ideal for lightweight multimodal deployments. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the Models section of SageMaker Studio or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

NVIDIA's Qwen3.6-35B-A3B-NVFP4 and Alibaba's Wan2.1-T2V-1.3B-Diffusers models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning agentic coding with long-context reasoning and lightweight text-to-video generation, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Qwen3.6-35B-A3B-NVFP4 is optimized for agentic coding, multimodal reasoning, and long-context understanding as the NVIDIA-quantized variant of Alibaba's Qwen3.6-35B-A3B. This Mixture-of-Experts model contains 35B total parameters with only 3B activated per token (8 of 256 experts), supporting a 262K-token context window extendable to ~1M via YaRN scaling. Quantized to NVFP4 using NVIDIA's ModelOpt framework, it preserves thinking across conversation turns, multi-token prediction, and tool calling for multi-step agent pipelines—all at a significantly reduced memory footprint. Wan2.1-T2V-1.3B-Diffusers excels in text-to-video generation on consumer-grade hardware. Built on the diffusion transformer paradigm with a novel Video Variational Autoencoder (VAE), this 1.3B-parameter model generates high-quality, physics-consistent video clips from text prompts while requiring only 8.19 GB of VRAM. It can produce a 5-second 480p video on an RTX 4090 in approximately 4 minutes, making it one of the most accessible open-source video generation models available. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

BM's granite-speech-4.1-2b, Kakao's kanana-2-30b-a3b-instruct, and the OpenFold Consortium's OpenFold3 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning multilingual speech recognition, bilingual agentic AI, and biomolecular structure prediction, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: granite-speech-4.1-2b is purpose-built for multilingual automatic speech recognition (ASR) and bidirectional speech translation (AST) across English, French, German, Spanish, Portuguese, and Japanese. This compact 2B-parameter speech-language model delivers a word error rate of 5.33% with a real-time factor of ~231, making it one of the most efficient ASR models in its class. Released under Apache 2.0, it integrates seamlessly into enterprise voice workflows for transcription, translation, and audio processing at scale. kanana-2-30b-a3b-instruct excels in bilingual Korean-English instruction following and agentic AI workflows. Developed by Kakao, it adopts a cutting-edge architecture featuring Multi-head Latent Attention (MLA) and Mixture-of-Experts (MoE), activating only 3B of its 30B total parameters per forward pass for superior throughput. Post-trained with supervised fine-tuning and reinforcement learning, it supports up to 128K tokens via YaRN scaling and is designed to function as an AI collaborator that understands context and acts proactively. OpenFold3 provides all-atom biomolecular complex structure prediction for proteins, DNA, RNA, and small-molecule ligands. Developed by the OpenFold Consortium and the AlQuraishi Lab at Columbia University, this diffusion-based model extends structure prediction beyond single proteins to model multi-chain complexes and heterogeneous biomolecular interactions. It supports computer-aided drug design and is applicable across academic and pharmaceutical research labs. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

Mistral AI's Ministral-3-3B-Instruct-2512 and Ministral-3-8B-Instruct-2512 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models from the Ministral 3 family bring compact, vision-capable language models purpose-built for edge deployment and resource-constrained environments, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Ministral-3-3B-Instruct-2512 is engineered for ultra-lightweight edge deployment with multimodal understanding. Comprising a 3.4B language model and a 0.4B vision encoder, it fits in just 8GB of VRAM in FP8 while supporting a 256K-token context window. It offers vision analysis, multilingual instruction following across dozens of languages (including English, French, Spanish, German, Chinese, Japanese, Korean, and Arabic), strong system-prompt adherence, and native function calling with structured JSON output—all under the Apache 2.0 license. Ministral-3-8B-Instruct-2512 delivers frontier-class capabilities comparable to its larger Mistral Small 3.2 24B counterpart in a compact 8B form factor. Built with an 8.4B language model and a 0.4B vision encoder, it fits in 12GB of VRAM in FP8 and features an interleaved sliding-window attention pattern for faster, memory-efficient inference. It shares the same vision, multilingual, agentic, and function-calling capabilities as its 3B sibling while offering stronger reasoning and generation performance. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Mistral AI's Ministral-3-3B-Instruct-2512 and Ministral-3-8B-Instruct-2512 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models from the Ministral 3 family bring compact, vision-capable language models purpose-built for edge deployment and resource-constrained environments, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Ministral-3-3B-Instruct-2512 is engineered for ultra-lightweight edge deployment with multimodal understanding. Comprising a 3.4B language model and a 0.4B vision encoder, it fits in just 8GB of VRAM in FP8 while supporting a 256K-token context window. It offers vision analysis, multilingual instruction following across dozens of languages (including English, French, Spanish, German, Chinese, Japanese, Korean, and Arabic), strong system-prompt adherence, and native function calling with structured JSON output—all under the Apache 2.0 license. Ministral-3-8B-Instruct-2512 delivers frontier-class capabilities comparable to its larger Mistral Small 3.2 24B counterpart in a compact 8B form factor. Built with an 8.4B language model and a 0.4B vision encoder, it fits in 12GB of VRAM in FP8 and features an interleaved sliding-window attention pattern for faster, memory-efficient inference. It shares the same vision, multilingual, agentic, and function-calling capabilities as its 3B sibling while offering stronger reasoning and generation performance. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

NVIDIA's Qwen3.6-35B-A3B-NVFP4 and Alibaba's Wan2.1-T2V-1.3B-Diffusers models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning agentic coding with long-context reasoning and lightweight text-to-video generation, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Qwen3.6-35B-A3B-NVFP4 is optimized for agentic coding, multimodal reasoning, and long-context understanding as the NVIDIA-quantized variant of Alibaba's Qwen3.6-35B-A3B. This Mixture-of-Experts model contains 35B total parameters with only 3B activated per token (8 of 256 experts), supporting a 262K-token context window extendable to ~1M via YaRN scaling. Quantized to NVFP4 using NVIDIA's ModelOpt framework, it preserves thinking across conversation turns, multi-token prediction, and tool calling for multi-step agent pipelines—all at a significantly reduced memory footprint. Wan2.1-T2V-1.3B-Diffusers excels in text-to-video generation on consumer-grade hardware. Built on the diffusion transformer paradigm with a novel Video Variational Autoencoder (VAE), this 1.3B-parameter model generates high-quality, physics-consistent video clips from text prompts while requiring only 8.19 GB of VRAM. It can produce a 5-second 480p video on an RTX 4090 in approximately 4 minutes, making it one of the most accessible open-source video generation models available. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Google DeepMind's Gemma-4-31B-it-assistant and NVIDIA's Gemma-4-31B-IT-NVFP4 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring the flagship Gemma 4 31B dense architecture to enterprise workloads in both full-precision and optimized quantized variants, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Gemma-4-31B-it-assistant is built for multimodal reasoning, coding, and agentic workflows as the assistant-tuned variant of Google's flagship 31B dense model. It handles text and image inputs (including video as frame sequences) and generates text output, with a 256K-token context window and support for over 140 languages. Ranked #3 among open models on the Arena AI text leaderboard—outcompeting models 20x its size—it features a hybrid attention mechanism interleaving local sliding-window and full global attention with native function calling for building autonomous agents. Gemma-4-31B-IT-NVFP4 delivers the same Gemma 4 31B capabilities at a fraction of the memory footprint. Quantized with NVIDIA's ModelOpt framework to 4-bit FP4 precision, it reduces memory usage to ~18.5 GB (68% smaller than the base model) and achieves approximately 2.5x faster inference while retaining 97–99% of the original model's quality. Ideal for cost-efficient, high-throughput production deployments on NVIDIA RTX, DGX Spark, and data center GPUs. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

BM's granite-speech-4.1-2b, Kakao's kanana-2-30b-a3b-instruct, and the OpenFold Consortium's OpenFold3 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning multilingual speech recognition, bilingual agentic AI, and biomolecular structure prediction, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: granite-speech-4.1-2b is purpose-built for multilingual automatic speech recognition (ASR) and bidirectional speech translation (AST) across English, French, German, Spanish, Portuguese, and Japanese. This compact 2B-parameter speech-language model delivers a word error rate of 5.33% with a real-time factor of ~231, making it one of the most efficient ASR models in its class. Released under Apache 2.0, it integrates seamlessly into enterprise voice workflows for transcription, translation, and audio processing at scale. kanana-2-30b-a3b-instruct excels in bilingual Korean-English instruction following and agentic AI workflows. Developed by Kakao, it adopts a cutting-edge architecture featuring Multi-head Latent Attention (MLA) and Mixture-of-Experts (MoE), activating only 3B of its 30B total parameters per forward pass for superior throughput. Post-trained with supervised fine-tuning and reinforcement learning, it supports up to 128K tokens via YaRN scaling and is designed to function as an AI collaborator that understands context and acts proactively. OpenFold3 provides all-atom biomolecular complex structure prediction for proteins, DNA, RNA, and small-molecule ligands. Developed by the OpenFold Consortium and the AlQuraishi Lab at Columbia University, this diffusion-based model extends structure prediction beyond single proteins to model multi-chain complexes and heterogeneous biomolecular interactions. It supports computer-aided drug design and is applicable across academic and pharmaceutical research labs. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Google DeepMind's Gemma-4-31B-it-assistant and NVIDIA's Gemma-4-31B-IT-NVFP4 models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring the flagship Gemma 4 31B dense architecture to enterprise workloads in both full-precision and optimized quantized variants, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Gemma-4-31B-it-assistant is built for multimodal reasoning, coding, and agentic workflows as the assistant-tuned variant of Google's flagship 31B dense model. It handles text and image inputs (including video as frame sequences) and generates text output, with a 256K-token context window and support for over 140 languages. Ranked #3 among open models on the Arena AI text leaderboard—outcompeting models 20x its size—it features a hybrid attention mechanism interleaving local sliding-window and full global attention with native function calling for building autonomous agents. Gemma-4-31B-IT-NVFP4 delivers the same Gemma 4 31B capabilities at a fraction of the memory footprint. Quantized with NVIDIA's ModelOpt framework to 4-bit FP4 precision, it reduces memory usage to ~18.5 GB (68% smaller than the base model) and achieves approximately 2.5x faster inference while retaining 97–99% of the original model's quality. Ideal for cost-efficient, high-throughput production deployments on NVIDIA RTX, DGX Spark, and data center GPUs. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Meta's Muse-Glimmer-30B and Alibaba's Qwen 3.8-27B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning autonomous local agentic workflows and multimodal long-horizon reasoning, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: Muse-Glimmer-30B is engineered for autonomous agentic tasks with multi-step reasoning, tool use, and failure recovery. This 30B-parameter dense model from Meta Superintelligence Lab combines a dedicated ~1.8B ViT-G/14 perception encoder with interleaved text and image inputs, a 131K+ context window, and selectable reasoning strength (low through extra-high). Released under Apache 2.0, it handles sequential tool calls, recovers from failures, and operates entirely without cloud infrastructure which is ideal for always-on enterprise agents. Qwen 3.8-27B excels in coding, multi-step agentic tasks, and multimodal understanding across text, images, and video. A dense 27B-parameter native vision-language model with a 262K context window (extendable to ~1M via YaRN scaling), it delivers substantial gains over its predecessor with adjustable reasoning effort levels. Scoring 61.7 on SWE-bench Pro and running at ~17GB quantized, it carries complex multi-step tasks through to completion with greater reliability. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

NVIDIA's Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models form the Cosmos 3 family of open, frontier omnimodal world models for physical AI, enabling customers to build robots, autonomous vehicles, and vision AI that perceive, reason, plan, and act in the physical world. These models address different physical AI challenges with specialized capabilities: Cosmos3-Edge is engineered for on-device robot control and real-time visual reasoning on edge hardware. This 4B-parameter omni-model (with a 2B Nemotron-based reasoner) operates at robot-control resolution (640×360), delivering real-time reasoning and generating 32 actions per inference at 15 Hz on NVIDIA Jetson Thor. It supports 256p and 480p video at 12–30 FPS, bringing frontier physical AI capabilities directly to embedded systems. Cosmos3-Nano excels in physics-aware world generation and physical reasoning as a compact 16B-parameter omnimodal model. It processes combinations of text, image, video, audio, and action trajectories to produce corresponding outputs, enabling robots and vision AI agents to reason using prior knowledge, physics understanding, and common sense. It supports chain-of-thought reasoning over text, images, and video with resolutions up to 720p. Cosmos3-Super provides the highest-fidelity world generation and simulation in the Cosmos 3 family at 64B parameters. It jointly processes and generates language, images, video, audio, and action sequences within a unified Mixture-of-Transformers architecture, supporting resolutions up to 720p across multiple aspect ratios. Ideal for large-scale simulation, synthetic data generation, and policy learning workflows. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

NVIDIA's Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models form the Cosmos 3 family of open, frontier omnimodal world models for physical AI, enabling customers to build robots, autonomous vehicles, and vision AI that perceive, reason, plan, and act in the physical world. These models address different physical AI challenges with specialized capabilities: Cosmos3-Edge is engineered for on-device robot control and real-time visual reasoning on edge hardware. This 4B-parameter omni-model (with a 2B Nemotron-based reasoner) operates at robot-control resolution (640×360), delivering real-time reasoning and generating 32 actions per inference at 15 Hz on NVIDIA Jetson Thor. It supports 256p and 480p video at 12–30 FPS, bringing frontier physical AI capabilities directly to embedded systems. Cosmos3-Nano excels in physics-aware world generation and physical reasoning as a compact 16B-parameter omnimodal model. It processes combinations of text, image, video, audio, and action trajectories to produce corresponding outputs, enabling robots and vision AI agents to reason using prior knowledge, physics understanding, and common sense. It supports chain-of-thought reasoning over text, images, and video with resolutions up to 720p. Cosmos3-Super provides the highest-fidelity world generation and simulation in the Cosmos 3 family at 64B parameters. It jointly processes and generates language, images, video, audio, and action sequences within a unified Mixture-of-Transformers architecture, supporting resolutions up to 720p across multiple aspect ratios. Ideal for large-scale simulation, synthetic data generation, and policy learning workflows. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

NVIDIA's LocateAnything-3B, Qwen's Qwen-AgentWorld-35B-A3B, and Qwen's Qwen3.5-122B-A10B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning visual grounding, agent environment simulation, and large-scale multimodal reasoning, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. These models address different enterprise AI challenges with specialized capabilities: LocateAnything-3B is optimized for fast, high-quality visual grounding and object localization from natural language instructions. It uses a Parallel Box Decoding (PBD) framework that decodes bounding boxes and points as atomic units in a single step, preserving geometric coherence and unlocking substantial parallelism. It enables precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI applications. Qwen-AgentWorld-35B-A3B excels in simulating agent environments across seven interaction domains: tool calling, search, terminal, software engineering, Android, web, and OS interaction. It is the first language world model to cover all seven domains within a single model, predicting next environment states given an agent's action and interaction history via long chain-of-thought reasoning—trained on over 10 million real-world interaction trajectories. Qwen3.5-122B-A10B provides high-performance multimodal reasoning with production-friendly efficiency. It features 122B total parameters with only 10B activated per token through a hybrid architecture integrating Gated Delta Networks with sparse Mixture-of-Experts (256 experts), delivering strong reasoning, coding, agents, and visual understanding performance with a native 262K context window and minimal latency overhead. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.  

Z.ai's GLM-5.2 FP8, NVIDIA's Nemotron-Nano-12B-v2, and Z.ai's GLM-OCR models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning long-horizon agentic engineering, efficient hybrid reasoning, and advanced document understanding, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. GLM-5.2 FP8 is optimized for long-horizon tasks and agentic engineering workflows such as full-cycle software development from requirements to deployment. It delivers a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, provides a truly usable 1M-token context window, enabling it to handle project-level engineering context, execute long-running tasks reliably, follow engineering standards consistently, and complete full development workflows in a single task. NVIDIA-Nemotron-Nano-12B-v2 excels in unified reasoning and non-reasoning tasks with high inference throughput, making it ideal for enterprise applications requiring both accuracy and efficiency. It uses a hybrid Mamba-2 and Transformer architecture with a 128K context length, generating reasoning traces before concluding with final responses. Its compact 12B parameter design achieves comparable or better accuracy than leading open models while delivering up to 6x higher inference throughput. GLM-OCR provides accurate, fast, and comprehensive document understanding for complex real-world materials including scanned PDFs, handwritten notes, dense academic papers with formulas, multi-column tables, code documentation, and multilingual text. This 0.9B-parameter multimodal model reconstructs structure, tables, and formulas into clean Markdown, JSON, or LaTeX, with latency low enough for real-time services and edge devices—ideal for large-scale document processing and invoice extraction workflows. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

Redis's langcache-embed-v3-small, JetBrains' Mellum2-12B-A2.5B-Thinking, and LightOn's LightOnOCR-2-1B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning semantic caching optimization, code-focused reasoning, and end-to-end document OCR, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. langcache-embed-v3-small is optimized for semantic caching in LLM applications. It maps sentences and paragraphs into a dense vector space purpose-built for identifying semantically equivalent queries regardless of phrasing, enabling intelligent cache hits that reduce redundant LLM calls and accelerate response times in high-volume inference workloads. Mellum2-12B-A2.5B-Thinking excels in code generation, debugging, multi-step reasoning, and agentic coding workflows. It uses a Mixture-of-Experts architecture (64 experts, 8 activated per token), activating only 2.5B of its 12B total parameters per forward pass with a 131,072-token context length. It emits explicit chain-of-thought reasoning traces before final answers, delivering high-throughput, low-latency inference ideal for routing, RAG, sub-agents, and private deployments. LightOnOCR-2-1B provides end-to-end multilingual document-to-text conversion for PDFs, scans, and images without brittle OCR pipelines. This 1B-parameter vision-language model directly transduces page images into clean, naturally ordered text, achieving state-of-the-art performance on OlmOCR-Bench while being ~9× smaller and significantly faster than competing approaches. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning efficient image generation decoding and unified multimodal understanding, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. FLUX.2-small-decoder is optimized for faster image decoding with lower VRAM usage in FLUX.2 image generation pipelines. It is a distilled VAE decoder that serves as a drop-in replacement for the standard FLUX.2 decoder, delivering approximately 1.4× faster decoding speed at 1.4× lower VRAM consumption with minimal to zero quality loss. Benefits increase at higher resolutions where the decoder processes more pixels, making it ideal for production-grade image generation workloads at scale. gemma-4-12B-it excels in unified multimodal understanding across text, image, and audio inputs with native support for function calling and agentic workflows. It features an encoder-free architecture where all modalities flow directly into a single decoder-only transformer, delivering performance nearing Google's larger 26B MoE model at less than half the memory footprint. Compact enough to run on 16GB of RAM, it enables powerful multimodal and agentic experiences for enterprise deployments. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

Black Forest Labs' FLUX.2-small-decoder and Google's gemma-4-12B-it models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These two models bring specialized capabilities spanning efficient image generation decoding and unified multimodal understanding, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. FLUX.2-small-decoder is optimized for faster image decoding with lower VRAM usage in FLUX.2 image generation pipelines. It is a distilled VAE decoder that serves as a drop-in replacement for the standard FLUX.2 decoder, delivering approximately 1.4× faster decoding speed at 1.4× lower VRAM consumption with minimal to zero quality loss. Benefits increase at higher resolutions where the decoder processes more pixels, making it ideal for production-grade image generation workloads at scale. gemma-4-12B-it excels in unified multimodal understanding across text, image, and audio inputs with native support for function calling and agentic workflows. It features an encoder-free architecture where all modalities flow directly into a single decoder-only transformer, delivering performance nearing Google's larger 26B MoE model at less than half the memory footprint. Compact enough to run on 16GB of RAM, it enables powerful multimodal and agentic experiences for enterprise deployments. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Redis's langcache-embed-v3-small, JetBrains' Mellum2-12B-A2.5B-Thinking, and LightOn's LightOnOCR-2-1B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These three models bring specialized capabilities spanning semantic caching optimization, code-focused reasoning, and end-to-end document OCR, enabling customers to deploy high-performance, scalable AI solutions on AWS infrastructure. langcache-embed-v3-small is optimized for semantic caching in LLM applications. It maps sentences and paragraphs into a dense vector space purpose-built for identifying semantically equivalent queries regardless of phrasing, enabling intelligent cache hits that reduce redundant LLM calls and accelerate response times in high-volume inference workloads. Mellum2-12B-A2.5B-Thinking excels in code generation, debugging, multi-step reasoning, and agentic coding workflows. It uses a Mixture-of-Experts architecture (64 experts, 8 activated per token), activating only 2.5B of its 12B total parameters per forward pass with a 131,072-token context length. It emits explicit chain-of-thought reasoning traces before final answers, delivering high-throughput, low-latency inference ideal for routing, RAG, sub-agents, and private deployments. LightOnOCR-2-1B provides end-to-end multilingual document-to-text conversion for PDFs, scans, and images without brittle OCR pipelines. This 1B-parameter vision-language model directly transduces page images into clean, naturally ordered text, achieving state-of-the-art performance on OlmOCR-Bench while being ~9× smaller and significantly faster than competing approaches. With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.