Software · head to head
Milvus vs Weaviate
Milvus
Software
Open-source vector database for scalable similarity search
- From
- Free
- Rated
- -
The short version
- Each has a real cost: Milvus vector dimensions are capped at 32,768; Weaviate the free tier caps at 100,000 objects, 1 GB of memory and a single collection
- They diverge on capability: Milvus covers Billion-scale vectors, Weaviate covers Vector and keyword search.
Where they differ
Only the attributes on which Milvus and Weaviate actually diverge.
Identical on both: starting price (Free), pricing model (freemium), free tier (Yes), platforms (Linux, Mac, Windows, Web), user rating (Not yet rated), category (Unknown).
What each one covers
Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.
Only in Milvus
- Billion-scale vectors
- Multiple index types
- GPU acceleration
- Data partitioning
- PyTorch
- TensorFlow
Only in Weaviate
- Vector and keyword search
- Built-in vectorizers
- GraphQL API
- Multi-tenancy
- OpenAI
- Cohere
Both cover
- Hybrid search
- Hugging Face
- LangChain
- LlamaIndex
- Linux support
- Mac support
- Windows support
- Web support
What people use each for
The jobs each tool is most often brought in to do.
Milvus
- Self hosting a vector database for semantic searchnot Weaviate
- Storing and querying embeddings for retrieval augmented generationnot Weaviate
- Similarity search over images, audio or text at scalenot Weaviate
Weaviate
- Running a vector database for semantic and hybrid searchnot Milvus
- Generating and storing embeddings alongside the objects they describenot Milvus
Where each one falls short
Documented limitations, not opinions. Every one is a constraint you would hit in normal use.
Milvus
- Vector dimensions are capped at 32,768
- A collection is limited to 64 fields, 1,024 partitions and 16 shards
- Only 1 index is allowed per field
- Search returns at most 16,384 vectors as top-k, and nq is capped at 16,384
- Input and output per RPC is capped at 64 MB for insert, search and query
- VARCHAR values are limited to 65,535 characters
- Data loaded into query nodes cannot exceed 90% of available memory
- An instance supports at most 65,536 collections
Weaviate
- The free tier caps at 100,000 objects, 1 GB of memory and a single collection
- Billing is per million vector dimensions rather than per record, so wider embeddings cost proportionally more for the same object count
- Premium is a prepaid contract starting at $400 a month rather than pay as you go
- Storage rates do not fall consistently with tier, and Premium Dedicated is $0.1505 per GiB against $0.12 on the cheaper Flex plan
- The Query Agent is metered separately, free to 1,000 requests a month and $30 a month plus overage beyond
Pricing, plan by plan
Milvus
Free- Open SourceFree
- Full features
- Self-hosted
- Community support
- Zilliz CloudFree
- Managed service
- Free tier available
Weaviate
Free- Open SourceFree
- Full features
- Self-hosted
- ServerlessFree
- Managed service
- Auto-scaling
Which should you pick?
Choose Milvus if
- You need billion-scale vectors.
- You want to start without paying.
- You work on Linux, Mac, Windows, Web.
- You also want multiple index types.
Choose Weaviate if
- You need vector and keyword search.
- You want to start without paying.
- You work on Linux, Mac, Windows, Web.
- You also want built-in vectorizers.
Questions people ask
- Is Milvus or Weaviate better?
- Neither clearly leads. Milvus starts at Free and Weaviate at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
- Which is cheaper, Milvus or Weaviate?
- Milvus starts at Free and Weaviate at Free.
- Does Milvus or Weaviate run on more platforms?
- Both run on Linux, Mac, Windows, Web, so platform support will not decide this one for you.
- Can I use Milvus for free?
- Both have a free tier, so you can try either at no cost before committing.
- What is Milvus best used for?
- Milvus is most often used for self hosting a vector database for semantic search, storing and querying embeddings for retrieval augmented generation, similarity search over images, audio or text at scale. Of those, self hosting a vector database for semantic search and storing and querying embeddings for retrieval augmented generation are not what Weaviate is typically brought in for.
- What can Milvus do that Weaviate cannot?
- Milvus covers Billion-scale vectors, Multiple index types, GPU acceleration, Data partitioning. Weaviate covers Vector and keyword search, Built-in vectorizers, GraphQL API, Multi-tenancy. Both handle Hybrid search, Hugging Face, LangChain, LlamaIndex.