Approved models
8
Records published from this collection
Provider information
lab
Review approach
Verify each model’s source, terms, capabilities, and current availability
IBM Granite publishes model families for language, reasoning and other application tasks. Compare the actual checkpoint size, native context and chat template before selecting a local deployment. Where long-context extensions are documented, evaluate them separately from the native configuration.
Review each record individually; collection membership does not imply a recommendation or guarantee of availability.
| Granite 4.2 8B IBM Granite | 41.8 | 131.07K | — | — | — |
| Granite 4.2 30B IBM Granite | 41.8 | 131.07K | — | — | — |
| Granite 4.2 3B IBM Granite | 41.8 | 131.07K | — | — | — |
| Granite Speech 5.0 TurboCTC IBM Granite | 5.0 | — | — | — | — |
| ibm-granite/granite-4.1-8b IBM Granite | 0.0 | — | — | — | — |
| ibm-granite/granite-embedding-reranker-english-r2 IBM Granite | 5.0 | — | — | — | — |
| ibm-granite/granite-embedding-small-english-r2 IBM Granite | 5.0 | — | — | — | — |
| ibm-granite/granite-vision-3.3-2b IBM Granite | 5.0 | — | — | — | — |
1–8 of 8 models · select a column to sort
About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.