New AI Models from Redis, JetBrains, and LightOn Now on SageMaker JumpStart
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. These additions expand the foundation model portfolio, offering specialized capabilities for semantic caching, code-focused reasoning, and end-to-end document OCR. AWS customers can now deploy these high-performance, scalable AI solutions with ease to optimize LLM applications, enhance coding workflows, and process documents. Each model is optimized for specific use cases, from reducing redundant LLM calls to enabling agentic coding and multilingual document-to-text conversion.
- →Redis langcache-embed-v3-small for LLM Semantic Caching
- →JetBrains Mellum2-12B-A2.5B-Thinking for Code Reasoning
- →LightOn LightOnOCR-2-1B for End-to-End Document OCR
Features (3) ›
- Redis langcache-embed-v3-small for LLM Semantic Caching
This model is optimized for semantic caching in LLM applications, mapping sentences into a dense vector space to identify semantically equivalent queries. It enables intelligent cache hits that reduce redundant LLM calls and accelerate response times in high-volume inference workloads.
- JetBrains Mellum2-12B-A2.5B-Thinking for Code Reasoning
Mellum2-12B-A2.5B-Thinking excels in code generation, debugging, multi-step reasoning, and agentic coding workflows using a Mixture-of-Experts architecture. It emits explicit chain-of-thought reasoning traces, providing high-throughput and low-latency inference for routing, RAG, and sub-agents.
- LightOn LightOnOCR-2-1B for End-to-End Document OCR
This 1B-parameter vision-language model provides end-to-end multilingual document-to-text conversion for PDFs, scans, and images without brittle OCR pipelines. It directly transduces page images into clean, naturally ordered text, achieving state-of-the-art performance while being significantly smaller and faster.
https://aws.amazon.com/about-aws/whats-new/2026/01/langcache-embed-v3-small-mellum2-12B-A2.5B-thinking-lightOnOCR-2-1B-on-sagemaker-jumpstart/
Related releases
- AWS Blog: Unified Access Control for Enterprise Lakehouses AWS Big Data Blog ·
- AWS Glue integrates with SageMaker Unified Studio for one-click data access AWS What's New ·
- NVIDIA and Qwen AI Models Now on Amazon SageMaker JumpStart AWS What's New ·
- NVIDIA Nemotron 3.5 Lightning AI Model Now Available on Amazon SageMaker JumpStart AWS What's New ·
- New GLM-5.2 FP8, Nemotron-Nano-12B-v2, and GLM-OCR models on SageMaker JumpStart AWS What's New ·
- FLUX.2-small-decoder and gemma-4-12B-it Models Now on Amazon SageMaker JumpStart AWS What's New ·