IBM · bert
Can I run granite-embedding?
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextgranite-embedding system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| granite-embedding:30m30M parameters (tag)Maximum context unavailableBuild sourceCatalog checked 2026-10-13 | F16 | 0.1 GB | ~0.6 GB |
| granite-embedding:278m278M parameters (tag)Maximum context unavailableBuild sourceCatalog checked 2026-10-13 | F16 | 0.5 GB | ~1.0 GB |
Showing the 2 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run granite-embedding locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull granite-embedding:30m - 3.Use the Ollama embedding API with this tag. Embedding vectors are used for search and retrieval; this is not a chat model.
Frequently asked questions about granite-embedding
- How much VRAM do I need to run granite-embedding?
- At 4K context, the smallest published build of granite-embedding (F16) needs roughly 0.6 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run granite-embedding without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 0.6 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- How big is the granite-embedding download?
- The smallest published build is 0.1 GB. There are 2 builds in total, the largest being 0.5 GB. Leave some extra free disk space beyond the download itself.
- How do I run granite-embedding locally?
- Install Ollama, then download a specific build with "ollama pull granite-embedding:30m". This is an embedding model: use the embedding API with a supported client, not an interactive chat prompt.
Will granite-embedding run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026