Qdrant
Hacker ApprovedThe most recommended of 10 vector databases
People recommend Qdrant as an easy-to-run vector database with solid performance, especially for self-hosting and local RAG setups. Critics report shard failures and out-of-memory crashes at large scale.
People recommend Qdrant as an easy-to-run vector database with solid performance, especially for self-hosting and local RAG setups. Critics report shard failures and out-of-memory crashes at large scale.
25 people gave an opinion
- recommend it
- 22
- criticize it
- 3
- approval share
- 88%
Recommended in 10 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 22 people recommend itNeeds 10 or more, met.
- 7.3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 10 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Easy to set up and run
“it's pretty easy to run your own RAG locally also using a Vector Database like Qdrant for persistence”
Comment from 26 Aug 2026 in “RAG Is Simpler Than You Think” “Qdrant: Easy to use, solid performance, great for self-hosting”
Comment from 5 Nov 2025 in “Evaluate Your Own RAG, Why Best Practices Failed Us” “simple lil setup with qdrant”
Comment from 15 Jan 2026 in “Ask HN: How are you doing RAG locally?” Good for self-hosting and local RAG
“it's pretty easy to run your own RAG locally also using a Vector Database like Qdrant for persistence”
Comment from 26 Aug 2026 in “RAG Is Simpler Than You Think” “I run a dockerized version of qdrant for RAG related stuff and have been pretty happy with it.”
Comment from 22 Jun 2026 in “Ask HN: What are some rock solid open source vector databases” “For fuzzy similarity search over unstructured documents Qdrant and Chroma are the right tools.”
Comment from 4 Mar 2026 in “Agent memory is structured not fuzzy.why are we all using vector DBs for it?” - Comment from 23 Aug 2026 in “A self hosted AI software factory”
Works in memory or on disk
“Qdrant is also a good default choice, since it can work in-memory for development”
Comment from 25 Jan 2026 in “ANN v3: 200ms p99 query latency over 100B vectors” “Qdrant supports storing embeddings in memory as well as in a local directory”
Comment from 15 Jan 2026 in “Ask HN: How are you doing RAG locally?” Solid performance and retrieval
“Qdrant: Easy to use, solid performance, great for self-hosting”
Comment from 5 Nov 2025 in “Evaluate Your Own RAG, Why Best Practices Failed Us” “Nice use of Qdrant for the retrieval layer.”
Comment from 21 Jul 2026 in “Show HN: LongTerMemory Study tool with no subscription built with QDrant and RAG”
Other vector databases people recommend
The four most recommended other vector databases, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| QdrantThis page | 22 | 3 | 88% | 10 | — | Approved |
| Chroma | 17 | 5 | 77% | 7 | — | Approved |
| sqlite-vec | 17 | 3 | 85% | 7 | — | Approved |
| turbopuffer | 13 | 2 | 87% | 8 | — | Approved |
| LanceDB | 12 | 2 | 86% | 7 | — | Approved |
What people said
20 of the 28 comments that mention it, newest first. Each links to the original comment.
“it's pretty easy to run your own RAG locally also using a Vector Database like Qdrant for persistence”
“store embeddings in local Qdrant”
“No longer need to store fp32 vectors if you don't need them”
“Nice use of Qdrant for the retrieval layer.”
“I actually don't really have any complaints at this time.”
“I run a dockerized version of qdrant for RAG related stuff and have been pretty happy with it.”
“I've had very good luck having my system search for available tool functions with natural language”
“spent a month setting up pinecone or qdrant and then realize they just needed search that worked”
“For fuzzy similarity search over unstructured documents Qdrant and Chroma are the right tools.”
“why you'd go with one of the least correct vendors”
“The number of people I know who’ve had unrecoverable shard failures on Qdrant is too high to take it seriously.”
“Qdrant is also a good default choice, since it can work in-memory for development”
“Qdrant supports storing embeddings in memory as well as in a local directory”
“simple lil setup with qdrant”
“the rest of them OOMKilled (out of memory error), including milvus, qdrant, and weaviate”
“ended up using qdrant instead”
“Qdrant (vectors), Redis (job queue), PaddleOCR, Spacy NER, BGE-M3 embeddings.”
“The dedicated vector search solutions solve all the issues you mentioned”
“I can see it as a built-in feature with Qdrant.”
“Qdrant: Easy to use, solid performance, great for self-hosting”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.