Ollama Library · bert
Can I run paraphrase-multilingual?
Sentence-transformers model that can be used for tasks like clustering or semantic search.
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 contextparaphrase-multilingual 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 |
|---|---|---|---|
| paraphrase-multilingual:278m278M parameters (tag)Maximum context unavailableBuild sourceCatalog checked 2026-10-13 | F16 | 0.5 GB | ~1.0 GB |
Showing the 1 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 paraphrase-multilingual locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull paraphrase-multilingual:278m - 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 paraphrase-multilingual
- How much VRAM do I need to run paraphrase-multilingual?
- At 4K context, the smallest published build of paraphrase-multilingual (F16) needs roughly 1.0 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 paraphrase-multilingual without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 1.0 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 paraphrase-multilingual download?
- The smallest published build is 0.5 GB. Leave some extra free disk space beyond the download itself.
- How do I run paraphrase-multilingual locally?
- Install Ollama, then download a specific build with "ollama pull paraphrase-multilingual:278m". This is an embedding model: use the embedding API with a supported client, not an interactive chat prompt.
Will paraphrase-multilingual 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