langcache-embed-v3-small, Mellum2-12B-A2.5B-Thinking, and LightOnOCR-2-1B models now available on Amazon SageMaker JumpStart
Sagemaker Jumpstart ยท 2026-08-10
Actions
Technical Details
| Regions | all |
|---|---|
| Cost Impact | Neutral |
What This Means
For DevOps Teams
Deploy the new langcache-embed-v3-small, Mellum2-12B-A2.5B-Thinking, and LightOnOCR-2-1B models on Amazon SageMaker JumpStart to leverage specialized AI capabilities for your applications.
For Platform Teams
Integrate the new langcache-embed-v3-small, Mellum2-12B-A2.5B-Thinking, and LightOnOCR-2-1B models into your AI architecture on Amazon SageMaker JumpStart to enhance performance and scalability of your AI solutions.
For Executives
Evaluate deploying the new langcache-embed-v3-small, Mellum2-12B-A2.5B-Thinking, and LightOnOCR-2-1B models on Amazon SageMaker JumpStart to enhance your AI solutions with specialized capabilities in semantic caching, code generation, and document OCR, driving higher performance and scalability.
Source
Related Sagemaker Jumpstart Updates
- GLM-5.2 FP8, NVIDIA-Nemotron-Nano-12B-v2 and GLM-OCR models now available on Amazon SageMaker JumpStart (2026-08-10)
- FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart (2026-08-10)
- Amazon SageMaker AI serverless model customization now supports full fine-tuning (2026-08-03)
- Amazon SageMaker Unified Studio brings richer Git version control to all project tools (2026-07-30)
- Announcing region expansion of G7e instances on SageMaker AI inference (2026-07-23)