作者： Jakub Rusinowski · 最后更新： 2026年8月15日
The Granite 4.0 generation, listed here for the one tier that has no Granite 4.1 counterpart: the 32B-total / 9B-active hybrid mamba-2 build. Granite models are finetuned from their base models on permissively-licensed open instruction datasets plus internally-collected synthetic data, with improved instruction-following and tool-calling aimed squarely at enterprise RAG and agent workloads. Apache 2.0. For the smaller sizes, see Granite 4.1 — those tiers are newer and supersede their 4.0 equivalents.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | Granite 4.0 Small-H 32B-A9B |
| Granite 4.0 Small-H 32B-A9B | Min 20 GB VRAM · Q4_K_M · 128,000 ctx · ollama run granite4:32b-a9b-h |
The cheapest GPU that runs IBM Granite 4.0 locally (min 20 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama then run: ollama run granite4:32b-a9b-h
Minimum VRAM: 20 GB. For best results use Q4_K_M quantization.
IBM Granite 4.0 needs about 20 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Granite 4.0 Small-H 32B-A9B (20 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — IBM Granite 4.0 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for IBM Granite 4.0 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run granite4:32b-a9b-h. This downloads IBM Granite 4.0 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.