# Granite 4.0 H Small Granite 4.0 H Small by IBM: no offer with a token price is listed at present. Profile and benchmarks are on this page. - [Compare offers](https://models.searchit-agent.ai/ui-fat/modelle_api?q=granite-4-0-h-small) - [View price history](https://models.searchit-agent.ai/ui-fat/modelle_api?q=granite-4-0-h-small) ## Profile | Profile | | |---|---| | Developer | IBM | | Type | Language models | | Origin | US | | Input types | text | | Context (tokens) | 131,072 | | Max. output (tokens) | – | | Reasoning | – | | Parameters (bn) | 32.21 | | Open weights | ✓ yes | | Licence | Apache-2.0 | | VRAM at 4-bit (GB) | 22 (RTX PRO 4000) | | Released | – | [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=granite-4-0-h-small) ## Offers with processing in the EU (0) No offers in this group. [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=granite-4-0-h-small) ## Offers outside the EU (0) No offers in this group. [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_api?q=granite-4-0-h-small) ## AI Act Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. [EU processing and AI Act](https://models.searchit-agent.ai/en/knowledge/eu-and-ai-act/) ## Benchmarks | Benchmarks | | |---|---:| | GPQA Diamond (Artificial Analysis) | 41.6 | | Humanity's Last Exam (Artificial Analysis) | 3.8 | | Vectara HHEM-2.3 | 5.2 | | Vectara HHEM-2.3 – antwortrate | 100 | | Vectara HHEM-2.3 – halluzination | 5.2 | | Structured Output Benchmark (SOB), arXiv 2604.25359 | 0.98 | | Structured Output Benchmark (SOB), arXiv 2604.25359 – json pass | 0.98 | | Structured Output Benchmark (SOB), arXiv 2604.25359 – wertgenauigkeit | 0.76 | _[Report an error on this page](https://models.searchit-agent.ai/en/report/report-error/?seite=https%3A%2F%2Fmodels.searchit-agent.ai%2Fen%2Fmodels%2Fgranite-4-0-h-small%2F)_ --- Prices as of 14 Oct 2026. Providers' list prices, without guarantee.