--- title: "Ollama Downloads: Is Local LLM Adoption Keeping Up?" date: 2026-09-22 url: https://modevc.com/charts/ollama-downloads-local-llm-adoption/ keywords: ["ollama downloads", "local llm adoption", "ollama vs openai api"] publisher: Mode VC --- # Ollama Downloads: Is Local LLM Adoption Keeping Up? Ollama's JavaScript client grew 2.1×, but the cloud SDKs grew 8.7×. Local AI is growing; it is not where most products are built. ## Chart: On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46 weeks. On PyPI, after its counting change, it is 21.5. Weekly downloads of the ollama client per 1,000 combined downloads of the OpenAI, Anthropic and Google SDKs. npm: complete weeks, 6 Oct 2025 – 30 Aug 2026. PyPI: complete weeks after the 25 Aug 2026 counting change only. | Registry | Week of | ollama | OpenAI + Anthropic + Google SDKs | per 1,000 | |---|---|---|---|---| | npm | 6 Oct 2025 | 0.32M | 11.7M | 27.2 | | npm | 13 Oct 2025 | 0.31M | 12.2M | 25.8 | | npm | 20 Oct 2025 | 0.32M | 11.7M | 27.1 | | npm | 27 Oct 2025 | 0.30M | 11.6M | 25.7 | | npm | 3 Nov 2025 | 0.29M | 12.2M | 23.5 | | npm | 10 Nov 2025 | 0.31M | 12.3M | 25.3 | | npm | 17 Nov 2025 | 0.43M | 13.3M | 32.4 | | npm | 24 Nov 2025 | 0.45M | 12.1M | 37.3 | | npm | 1 Dec 2025 | 0.53M | 14.4M | 36.8 | | npm | 8 Dec 2025 | 0.40M | 14.5M | 27.7 | | npm | 15 Dec 2025 | 0.29M | 14.4M | 20.3 | | npm | 22 Dec 2025 | 0.23M | 9.4M | 24.6 | | npm | 29 Dec 2025 | 0.24M | 9.6M | 24.9 | | npm | 5 Jan 2026 | 0.34M | 15.7M | 21.9 | | npm | 12 Jan 2026 | 0.35M | 16.7M | 20.8 | | npm | 19 Jan 2026 | 0.44M | 18.2M | 24.1 | | npm | 26 Jan 2026 | 0.60M | 21.8M | 27.6 | | npm | 2 Feb 2026 | 0.67M | 22.8M | 29.5 | | npm | 9 Feb 2026 | 0.59M | 23.9M | 24.8 | | npm | 16 Feb 2026 | 0.49M | 23.4M | 21 | | npm | 23 Feb 2026 | 0.43M | 28.8M | 14.9 | | npm | 2 Mar 2026 | 0.46M | 31.4M | 14.6 | | npm | 9 Mar 2026 | 0.48M | 35.4M | 13.5 | | npm | 16 Mar 2026 | 0.43M | 34.9M | 12.4 | | npm | 23 Mar 2026 | 0.47M | 35.9M | 13.1 | | npm | 30 Mar 2026 | 0.44M | 37.1M | 11.9 | | npm | 6 Apr 2026 | 0.46M | 40.1M | 11.4 | | npm | 13 Apr 2026 | 0.46M | 42.9M | 10.7 | | npm | 20 Apr 2026 | 0.47M | 45.3M | 10.4 | | npm | 27 Apr 2026 | 0.50M | 50.7M | 9.9 | | npm | 4 May 2026 | 0.56M | 48.0M | 11.6 | | npm | 11 May 2026 | 0.61M | 50.4M | 12 | | npm | 18 May 2026 | 0.58M | 54.0M | 10.7 | | npm | 25 May 2026 | 0.52M | 61.9M | 8.5 | | npm | 8 Jun 2026 | 0.54M | 65.2M | 8.3 | | npm | 15 Jun 2026 | 0.55M | 68.8M | 7.9 | | npm | 29 Jun 2026 | 0.52M | 63.7M | 8.1 | | npm | 13 Jul 2026 | 0.65M | 72.7M | 9 | | npm | 20 Jul 2026 | 0.65M | 74.7M | 8.7 | | npm | 27 Jul 2026 | 0.71M | 80.2M | 8.9 | | npm | 3 Aug 2026 | 0.66M | 79.3M | 8.3 | | npm | 17 Aug 2026 | 0.63M | 89.6M | 7 | | npm | 24 Aug 2026 | 0.67M | 101.8M | 6.6 | | PyPI | 31 Aug 2026 | 2.8M | 125.3M | 22.1 | | PyPI | 7 Sep 2026 | 2.8M | 128.6M | 21.8 | | PyPI | 14 Sep 2026 | 2.9M | 133.1M | 21.5 | Note: The ollama package is one client for a local model server. Apps can also reach local models through other clients, and local tools that are not on npm or PyPI are not counted, so this is a lower bound on local use. Downloads are installs (including CI), not users. PyPI changed how it counts on 25 Aug 2026; we use only whole weeks after that date and only ratios, never PyPI levels before and after. Weeks with an npm gap day are dropped. ## The signal - **Launches:** Of the 44 model launches in our feed from 6 Jul to 22 Sep, 14 were closed-weight, 1 was confirmed open-weight and 29 were unclear when we checked. - **npm:** ollama had 0.67M npm downloads in the week of 24 Aug, 2.1× the week of 6 Oct 2025. The three cloud SDKs grew 8.7×. - **PyPI:** In the week of 14 Sep, Python developers installed ollama 21.5 times per 1,000 cloud SDK installs, 3.3× the npm rate. ## The Mode read Our launch feed confirms open weights for 1 of the 44 models launched since 6 July; 14 are closed and the rest are unconfirmed. Open weights are what local AI runs on. So how much are developers building on local models compared with cloud APIs? Less and less, relative to the cloud. On npm, Ollama's client grew **2.1×**, but the OpenAI, Anthropic and Google SDKs together grew **8.7×**. Its rate fell from 27 to **6.6** installs per 1,000 cloud SDK installs, 4.1× lower. Python is different: in the week of 14 Sep, after PyPI's counting change, the rate there was **21.5**, 3.3× the latest JavaScript rate. JavaScript is where products ship to users, and there the cloud is winning by a wide and widening margin. Local models show up more in Python, the language of experiments, fine-tuning and data jobs. For founders, local AI is not a mass developer market. It is a sales motion: buyers who cannot send data to a cloud API, reached through the vendors and IT channels they already trust. > Local models win on privacy. The cloud wins on distribution, and it is pulling away. **What we would back:** Companies that package open-weight models for buyers who must keep data in-house, sold through channels those buyers already use. ## Sources - [npm registry downloads API](https://api.npmjs.org/downloads/range/2025-10-01:2026-10-06/ollama) - [pypistats.org API (post-25 Aug 2026 only)](https://pypistats.org/api/packages/ollama/overall) - [Official launch posts (launch feed, captured 7 Oct 2026)](https://www.anthropic.com/claude-opus-5-5)