Granite

Evidence (6)

• 8Hugging Face Blog·9/9/2026model_release
  IBM releases Granite Time Series PatchTST-FM-r2 with commercial-friendly license

  IBM has released Granite Time Series PatchTST-FM-r2, a new time-series foundation model for zero-shot forecasting. The model adds probabilistic forecasting, missing-value imputation, and a larger pretraining corpus, and is dual-licensed under Apache 2.0 and OpenMDW 1.0 for permissive commercial use.

• 7Hugging Face Blog·9/2/2026product_launch
  IBM Time Series Models Arrive on Confluent for Real-Time Intelligence

  IBM and Confluent are bringing IBM time series foundation models to Confluent Cloud in Early Access, with Confluent Platform support planned next. The models are designed to run on streaming data for forecasting, anomaly detection, optimization, and related decision-making tasks directly where business data moves.

• 7Ars Technica AI·8/25/2026model_release
  How Granite 4.2 Reasoning LLMs Were Built

  IBM and the Granite team detailed how Granite 4.2 was built as a new family of dense, decoder-only reasoning models in 3B, 8B, and 30B sizes. The models were pre-trained from scratch on about 15T tokens, then supervised fine-tuned and post-trained with multi-stage reinforcement learning, including agentic RL for tool use in the 8B and 30B versions. The release also adds thinking/non-thinking modes, low-effort reasoning, native tool calling, and an expanded 512K context window.

• 8Hugging Face Blog·5/14/2026model_release
  IBM Granite Releases Multilingual Embedding R2 Models

  IBM has released two Apache 2.0 multilingual embedding models based on ModernBERT: a 97M-parameter compact model and a 311M full-size model. The models support 200+ languages, 32K-token context, and code retrieval across nine programming languages, with strong retrieval benchmark results and Matryoshka support for the larger model.

• 7Hugging Face Blog·4/29/2026model_release
  Granite 4.1 LLMs: How They Are Built

  IBM’s Granite Team details how Granite 4.1 was trained, from data engineering through supervised fine-tuning and reinforcement learning. The family includes dense decoder-only models in 3B, 8B, and 30B sizes, trained on about 15 trillion tokens and extended to a 512K context window, with the 8B instruct model reportedly matching or exceeding the prior Granite 4.0-H-Small despite using fewer parameters.

• 6Hugging Face Blog·3/31/2026model_release
  Granite 4.0 3B Vision for Enterprise Document Understanding

  IBM Granite 4.0 3B Vision is a compact vision-language model for extracting information from enterprise documents, including tables, charts, and key-value pairs. It is delivered as a LoRA adapter on Granite 4.0 Micro and can be used standalone or with Docling for document-processing workflows.