Granite TimeSeries FlowState R1
Zero-shot forecasting of regularly sampled numerical time series across changing temporal resolutions
Current open-weight model; r1.1 revision available
Browse the AI models associated with IBM watsonx. Compare current and historical models by family, capabilities, context window, availability and intended use.
Zero-shot forecasting of regularly sampled numerical time series across changing temporal resolutions
Current open-weight model; r1.1 revision available
Japanese text generation, summarization, classification, extraction, question answering, and Japanese-English translation in legacy IBM enterprise deployments
Deprecated; withdrawn from IBM Software Hub 5.2.0 and removed from watsonx.ai in 2.2.0
Multilingual enterprise question answering, retrieval-augmented generation, summarization, extraction, classification, and text generation in English, German, Spanish, French, and Portuguese
Retired; deprecated January 15, 2025 and withdrawn from standard watsonx.ai availability April 16, 2025
Fine-tuning, domain adaptation, text generation, summarization, extraction, classification, and question answering
Available for deployment on demand in IBM watsonx.ai; also available as an Apache 2.0 open-weight model through IBM's Hugging Face organization.
Fine-tuning, long-context document processing, enterprise text classification, extraction, summarization, question answering, and self-managed deployment
Available; base model intended for fine-tuning and dedicated deployment
Self-hosted enterprise assistants, long-context document analysis, RAG, summarization, extraction, multilingual text workflows, and function calling
Available as an open-weight model; superseded by Granite-3.3-8B-Instruct for newer deployments
Long-context enterprise RAG, document and meeting summarization, information extraction, multilingual dialogue, code-related tasks, function calling, and self-hosted deployments
Available; legacy in some IBM watsonx catalogs
Local or dedicated enterprise assistants, RAG, long-document summarization, multilingual text workflows, coding assistance, reasoning, and resource-conscious inference
Available; open-weight model with local deployment and dedicated IBM watsonx deployment options
Self-hosted enterprise assistants, long-context RAG, summarization, multilingual text tasks, coding assistance, function calling, and cost-sensitive deployments.
Retired from IBM watsonx.ai deploy-on-demand service on 2026-02-22; open-weight checkpoint remains available for self-hosted and compatible third-party deployments.
Low-latency local inference, long-context text generation, RAG, multilingual assistants, coding assistance, and lightweight tool-calling agents
Current open-weight instruct model
Enterprise RAG, multi-tool agents, function calling, customer-support automation, multilingual instruction following, and long-context workloads
Available; open-weight instruct model
Efficient enterprise assistants, multilingual text generation, RAG, classification, extraction, summarization, coding assistance, fill-in-the-middle completion, structured JSON, and tool-calling workflows
Current; open-weight instruct model; available for download and listed for deploy-on-demand use in IBM watsonx.ai
Efficient local or private deployment, multilingual enterprise text processing, RAG, summarization, extraction, coding assistance, function calling, and lightweight AI assistants.
Currently available open-weight model; earlier-generation Granite model superseded by the newer Granite 4.2 family, with no verified deprecation or shutdown date.
Self-hosted enterprise assistants, multilingual text generation, RAG, coding assistance, structured extraction, and tool-calling agents
Current open-weight instruction model
Self-hosted enterprise assistants, long-context RAG, multilingual applications, coding, structured extraction, and tool-calling agents
Current open-weight instruct model; publicly available
Efficient reasoning, coding assistance, tool calling, multilingual dialogue, local deployment, and lightweight enterprise agents
Current; publicly available open-weight model
Local or self-hosted reasoning, coding assistants, tool calling, multilingual dialogue, retrieval-augmented generation, and agentic workflows
Current; open-weight and downloadable
Self-hosted enterprise reasoning, coding agents, multilingual applications, tool calling, long-context workflows, and organizations requiring Apache 2.0 licensing
Current; open-weight and available for download
Self-hosted English text generation, summarization, extraction, classification, experimentation with LAB-aligned open-weight models, and resource-conscious deployments
Withdrawn from IBM watsonx.ai on 2025-01-07; open-weight checkpoint remains available for self-hosted deployment
English enterprise chat, retrieval-augmented generation, question answering, summarization, extraction, and classification
Withdrawn; access ended January 19, 2025
Self-hosted coding assistants, code generation, code explanation, code conversion, repository-scale prompts, and historical or reproducible research
Retired; withdrawn from IBM watsonx.ai on 2025-07-17
Local code generation, explanation, repair, translation, and research with an open Apache 2.0 model
Deprecated; still publicly available for historical and scientific use
Schema linking and relevant-table or relevant-column selection in text-to-SQL pipelines
Available; deploy on demand only
Natural-language-to-SQL generation over structured databases, analytics assistants, and the SQL-generation stage of text-to-SQL pipelines.
Available; deploy-on-demand model in IBM watsonx.ai
Self-hosted coding assistants, code generation, code conversion, code explanation, and programming experiments where an Apache 2.0 open-weight model is preferred.
Available as an open-weight model and documented for IBM watsonx.ai deploy-on-demand use; deprecated and withdrawn from the watsonx.ai multitenant offering according to IBM's 2025 lifecycle notice.
Self-hosted code generation, code explanation, code repair, code conversion, coding assistants, and legacy Granite Code compatibility
Legacy/deprecated; available in some IBM watsonx environments and retained for historical or scientific use
Fast, low-footprint English semantic search, RAG retrieval, similarity matching, and vector indexing
Legacy; downloadable and usable, but superseded by Granite Embedding Small English R2
Low-latency multilingual semantic search, retrieval-augmented generation, vector search, document similarity, long-document retrieval, and cross-lingual code retrieval
Current; open-weight model
Low-cost multilingual semantic search, cross-lingual retrieval, vector databases, similarity matching, and RAG pipelines
Retired from IBM watsonx.ai; open-weight checkpoint remains available through IBM's Hugging Face organization
English semantic search, vector retrieval, RAG, similarity matching, enterprise knowledge-base search, and local embedding deployment
Legacy/superseded but downloadable and usable
Multilingual semantic search, retrieval-augmented generation, cross-lingual retrieval, long-document search, similarity, and code retrieval
Current open-weight model
English semantic search, vector retrieval, retrieval-augmented generation, document similarity, clustering, and enterprise information retrieval
Current open-weight model
Compact English semantic search, retrieval-augmented generation, document similarity, and private vector-search deployments
Current open-weight model
Multilingual semantic search, vector retrieval, RAG, clustering, similarity matching, and text classification features
Retired; shutdown completed 2026-08-08
Above-ground biomass mapping, forest monitoring, carbon-stock estimation, ecological analysis, and satellite-based remote-sensing research
Available open-weight model
Canopy-height mapping, forest monitoring, vegetation analysis, carbon-cycle research, ecological assessment, and remote-sensing experimentation.
Available as downloadable open-weight model; not deployed by an inference provider; IBM repository disclosure states that the project is not maintained as an IBM product.
Land surface temperature estimation, urban heat island analysis, satellite-based environmental monitoring, and temporal gap filling
Available as an open-weight model for local inference
Remote-sensing feature extraction, Earth-observation transfer learning, and regional flood-segmentation workflows using multispectral and SAR satellite imagery
Available as an open-weight research model; no hosted inference provider is currently listed
Spatial downscaling of weather forecasts, reanalysis data, and climate simulations
Current and available as downloadable open-weight model
Prompt and response safety classification, jailbreak detection, RAG groundedness and relevance checks, hallucination evaluation, and enterprise AI guardrails
Deprecated in IBM watsonx.ai documentation; open-weight model and official model materials remain available
AI safety guardrails, jailbreak detection, RAG groundedness and relevance checks, function-call hallucination detection, custom criteria evaluation, and best-of-N response ranking
Current and available as an open-weight model
Multilingual speech-to-text with speaker labels, word-level timestamps, keyword biasing, and self-hosted enterprise transcription
Current open-weight model
Multilingual offline transcription, speech-to-text, speech translation, subtitle generation, and domain-specific recognition with keyword biasing
Current open-weight model
High-throughput multilingual speech transcription where low inference latency is more important than maximum recognition accuracy.
Current; open-weight; Apache 2.0
High-throughput, low-latency English speech-to-text transcription on local, edge, and enterprise systems
Current; open-weight model
Fast local English speech-to-text transcription, edge-device ASR, research, browser demos, and high-throughput noncommercial batch processing
Current; research and noncommercial use only
Lightweight multivariate forecasting at minute- and hour-level resolutions, especially when 512 historical observations and a 96-point forecast horizon are appropriate.
Available
Zero-shot forecasting of demand, prices, energy loads, traffic, telemetry, and other regularly sampled numerical time series; probabilistic forecasts and uncertainty intervals; local or self-managed inference.
Current; open-weight model
High-throughput multivariate time-series forecasting, zero-shot or few-shot forecasting, probabilistic prediction, exogenous-variable forecasting, and CPU-friendly production deployment.
Current open-weight model family; available through the IBM Granite Hugging Face repository. No hosted inference provider deployment was listed on the reviewed model page.
Efficient multivariate forecasting for regularly sampled energy, traffic, manufacturing, network, sales, and sensor data
Available through IBM watsonx.ai; downloadable model branch
Multivariate forecasting when at least 1,536 historical observations per channel are available, especially demand, traffic, electricity, manufacturing, finance, and other minute- or hour-level forecasting tasks.
Available
Chart extraction, table parsing, semantic key-value extraction, visual document processing, and local enterprise RAG pipelines
Current and downloadable; newer Granite Vision 4.1 4B version available
Enterprise document understanding, chart and table extraction, OCR-oriented image analysis, visual question answering, and multimodal RAG
Available; legacy relative to Granite Vision 4.0 3B Vision
Structured extraction from charts, tables, invoices, forms, and enterprise document images
Current open-weight model
English semantic search, dense retrieval, vector indexing, duplicate-question matching, and lightweight retrieval-augmented generation
Deprecated; withdrawn in Dallas on 2026-09-08 and scheduled for withdrawal in other listed regions on 2027-01-12.
English semantic search, vector database indexing, retrieval-augmented generation, document matching, and query-passage retrieval
Deprecated; scheduled for withdrawal on 2027-01-12