IBM model product
A preliminary version of the smallest model in the upcoming Granite 4.0 family, released May 2025. It utilizes a novel hybrid Mamba-2/Transformer, fine-grained mixture of experts (MoE) architecture (7B total parameters, 1B active at inference). This preview version is partially trained (2.5T tokens) but demonstrates significant memory efficiency and performance potential, validated for at least 128K context length without positional encoding.
Updated Aug 10, 2026. Default version: IBM Granite 4.0 Tiny Preview
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version IBM Granite 4.0 Tiny Preview.
| AttaQ | 0.9 | 3 | 3 | 0.0% | C | |
| PopQA | 0.2 | 3 | 3 | 0.0% | C | |
| AlpacaEval 2.0 | 0.4 | 4 | 4 | 0.0% | C | |
| TruthfulQA | 0.6 | 10 | 18 | 47.1% | C | |
| BIG-Bench Hard | 0.6 | 16 | 21 | 25.0% | C | |
| Arena Hard | 0.3 | 26 | 26 | 0.0% | C | |
| DROP | 0.5 | 28 | 30 | 6.9% | C | |
| GSM8k | 0.7 | 44 | 48 | 8.5% | C | |
| HumanEval | 0.8 | 47 | 76 | 38.7% | C | |
| HumanEval+ | 0.8 | 53 | 76 | 30.7% | C | |
| IFEval | 0.6 | 62 | 65 | 4.7% | C | |
| MMLU | 0.6 | 97 | 100 | 3.0% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
The default version has no provider offering with current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| IBM Granite 4.0 Tiny Preview | 21.6 | 7B | N/A | N/A | No | Apache 2.0 |
A concise description based on the published model registry.
A preliminary version of the smallest model in the upcoming Granite 4.0 family, released May 2025. It utilizes a novel hybrid Mamba-2/Transformer, fine-grained mixture of experts (MoE) architecture (7B total parameters, 1B active at inference). This preview version is partially trained (2.5T tokens) but demonstrates significant memory efficiency and performance potential, validated for at least 128K context length without positional encoding.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about IBM Granite 4.0 Tiny.
IBM Granite 4.0 Tiny's default version was released on May 2, 2025.
No official standard PAYG price is currently available for IBM Granite 4.0 Tiny.
IBM Granite 4.0 Tiny is published under IBM in the model registry.
The current registry does not publish a context window for the default version.
No. The default version is not marked as having publicly available weights.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include Gemma 3n E4B LiteRT, Gemma 3 4B, Jamba 1.5 Mini.