Local-AI Index

How fast is self-hosted AI growing?

More and more companies prefer to run AI in-house — for privacy, cost and control. We count the daily downloads of the key tools that make it possible, turning the local-AI adoption race into something you can watch.

Docker images: the local-AI toolbox

Cumulative downloads of the most-used self-hosted AI images on Docker Hub — from model runtime to vector database. Sorted by downloads; the columns show the gain.

We start recording the daily gain today — the gain columns fill in from tomorrow. Today you see the current standing.

ToolDownloads24 h7 days30 days
Model runtime
Ollamaollama/ollama149.9M
vLLMvllm/vllm-openai26.4M
LocalAIlocalai/localai4.8M
LiteLLMlitellm/litellm774.4K
Text-Gen-WebUIatinoda/text-generation-webui252.5K
Chat & apps
Difylanggenius/dify-api20.7M
Flowiseflowiseai/flowise6.6M
LobeChatlobehub/lobe-chat5.8M
AnythingLLMmintplexlabs/anythingllm3.6M
RAG & vector DB
Milvusmilvusdb/milvus77.2M
Qdrantqdrant/qdrant35.9M
Weaviatesemitechnologies/weaviate18.9M
Chromachromadb/chroma6.1M
RAGFlowinfiniflow/ragflow3.3M
Orchestration & ops
n8nn8nio/n8n229.1M
Langfuselangfuse/langfuse11.9M

Ollama: the most popular local models

Which open models are people actually downloading to run locally? The top models in the Ollama library by downloads. Figures rounded (~) as reported by Ollama.

  1. 1llama3.1~116.7M
  2. 2deepseek-r1~89M
  3. 3nomic-embed-text~77M
  4. 4llama3.2~75M
  5. 5gemma3~38.3M
  6. 6qwen2.5~34M
  7. 7qwen3~31.7M
  8. 8mistral~30.7M
  9. 9gemma2~26.9M
  10. 10llama3~24.6M
  11. 11qwen2.5-coder~18.1M
  12. 12phi3~17.8M
  13. 13gemma4~16.7M
  14. 14qwen3.5~14.6M
  15. 15llava~14.3M
  16. 16mxbai-embed-large~12.1M
  17. 17gpt-oss~10.7M
  18. 18phi4~7.6M
  19. 19gemma~7.2M
  20. 20llama2~7.2M
  21. 21qwen~7.1M
  22. 22qwen3-coder~6.9M
  23. 23glm-ocr~6M
  24. 24qwen2~6M
  25. 25codellama~5.7M
  26. 26minicpm-v~5.3M
  27. 27mistral-nemo~5.2M
  28. 28tinyllama~5.2M
  29. 29bge-m3~5M
  30. 30llama3.2-vision~4.8M

How we measure

Honest and reproducible — we only read public, official counters.

  1. 1
    Docker Hub, exact

    For each image we read the public, exact total download count (pull_count) straight from Docker Hub — no key, no login.

  2. 2
    Ollama library

    From ollama.com we take the reported per-model downloads. These are rounded (e.g. "116.7M") — we mark them with ~.

  3. 3
    Once a day

    A job records one value per day. From the daily values we derive the gains (24 h / 7 days / 30 days).

  4. 4
    Forward only

    Neither source keeps a history. Our series can only be built forward and grows from the start — nobody can reconstruct it after the fact.

"Downloads" means how often an image or model was pulled — a proxy for adoption, not active use. CI systems and automated deployments count too. Official images that live only on ghcr.io (e.g. Open WebUI) can't be tracked, because there is no public download figure there.

Frequently asked

What is "local AI", anyway?

AI models you run on your own hardware or in your own cloud instead of via a third-party API. The upside: your data never leaves the building — a strong argument for privacy and GDPR.

Why downloads instead of user counts?

Downloads are the only public, reliable adoption metric that Docker Hub and Ollama expose. They track growth and trend well; they don't directly measure active use.

Why can nobody reconstruct this history?

Neither Docker Hub nor Ollama stores a history — they only ever show the current total, overwritten daily. Anyone who starts counting later has missed the past days forever. That's exactly what makes the series valuable.

Which tools are included?

A curated set of the most common self-hosted AI tools: model runtimes (Ollama, vLLM, LocalAI), chat UIs and app builders (LobeChat, AnythingLLM, Dify, Flowise), RAG and vector databases (Qdrant, Chroma, Weaviate, Milvus) and orchestration (n8n, Langfuse).

Sources: Docker Hub (hub.docker.com) and the Ollama library (ollama.com), both publicly available. Download counts are a proxy for adoption. No warranty for completeness or timeliness of individual values.

Local AI, cleanly set up

We bring self-hosted AI to your infrastructure — privacy-compliant, maintainable and productive.