Mistral AI's Ministral-3 Models Now on Amazon SageMaker JumpStart
Amazon SageMaker JumpStart now offers Mistral AI's Ministral-3-3B-Instruct-2512 and Ministral-3-8B-Instruct-2512 models. These compact, vision-capable language models are optimized for edge deployment and resource-constrained environments, expanding the foundation model portfolio for AWS customers. The 3B model is ultra-lightweight with multimodal understanding and a 256K context window, while the 8B version delivers frontier-class reasoning and generation. Both support multilingual instruction following, vision analysis, and native function calling.
Features (1) ›
- Mistral AI's Ministral-3 Models Available on SageMaker JumpStart
The Ministral-3-3B-Instruct-2512 model is optimized for ultra-lightweight edge deployment, offering multimodal understanding, a 256K-token context window, and native function calling within 8GB VRAM. The Ministral-3-8B-Instruct-2512 provides frontier-class reasoning and generation performance, fitting into 12GB VRAM while retaining similar vision, multilingual, and agentic capabilities.
https://aws.amazon.com/about-aws/whats-new/2026/01/ministral-3-3b-instruct-2512-ministral-3-8B-Instruct-2512-jumpstart/
Related releases
- SageMaker JumpStart adds NVIDIA Qwen3.6-35B-A3B-NVFP4 and Alibaba Wan2.1-T2V-1.3B models AWS What's New ·
- Amazon SageMaker JumpStart Adds Granite-Speech, Kanana-2, and OpenFold3 Models AWS What's New ·
- Gemma-4-31B LLMs from Google DeepMind and NVIDIA now on SageMaker JumpStart AWS What's New ·
- SageMaker HyperPod adds model caching for faster inference autoscaling AWS What's New ·
- Amazon SageMaker Feature Store now supports individual feature updates AWS What's New ·
- Amazon SageMaker Batch Transform adds support for G6e instances AWS What's New ·