Ollama

Ollama’s founders, Jeffrey Morgan and Michael Chiang, are both Canadian and met at the University of Waterloo, where they started their first company, Kitematic, which made Docker simple to run; Docker acquired it in 2015, and their work there became Docker Desktop, launched in 2016.⁠[1][2]

Ollama was initially based in Toronto and later moved to Silicon Valley; Morgan explained the move by saying “the Bay Area is the epicentre of AI.”⁠[2]

Ollama took part in Y Combinator’s Winter 2021 batch, with Jeffrey Morgan and Michael Chiang as founders and the one-line description “Get up and running with large language models.”⁠[3]

Ollama launched in 2023 to let developers download and run open-source large language models on their own computers. Its founders said open models were freely downloadable but hard to get working, so they shipped an app that could get the latest open models running with a single command and expose them through a simple API.⁠[2][1]

From August 2023 Ollama published guides on its blog to running open models such as Llama 2 and Code Llama locally.⁠[4]

On October 5, 2023 Ollama became available as an official Docker-sponsored open source image; on Linux it can use NVIDIANVIDIANVIDIA is an American semiconductor and computing technology company that provides graphics processing units, artificial intelligence infrastructure, networking interconnects, and computing software, and is listed on Nasdaq under the ticker NVDA.Open the full entry GPU acceleration inside Docker containers, while on the Mac it runs as a standalone application with GPU acceleration. It provides both a CLI and a REST API.⁠[5]

On January 23, 2024 Ollama released Python and JavaScript libraries. On February 8 it added initial experimental compatibility with the OpenAIOpenAIOpenAI is an artificial intelligence research and product organization founded in 2015 that develops the GPT model series, ChatGPT, Codex and a developer API, and conducts research on image, speech, video and intelligent agents. After its 2025 restructuring, the nonprofit OpenAI Foundation continues to control the for-profit OpenAI Group PBC. Its growth has involved large-scale fundraising and compute partnerships, and has also been accompanied by controversies over governance, copyright, privacy and AI safety.Open the full entry Chat Completions API, so tooling and applications built for OpenAI could be used with Ollama locally.⁠[4][6]

On February 15, 2024 Ollama released a Windows preview with built-in NVIDIA GPU acceleration, and from March 14 it supported AMDAMDAMD (Advanced Micro Devices, Inc.) is a publicly traded U.S. semiconductor company founded in 1969 and headquartered in Santa Clara, California; its stock trades on Nasdaq under the ticker AMD. The company develops CPUs, GPUs, FPGAs, adaptive systems-on-chip and related software, mainly for the data center, personal computer, gaming and embedded markets; its product brands include Ryzen, EPYC, Radeon and Instinct.Open the full entry graphics cards in preview on Windows and Linux.⁠[7][8]

On May 20, 2024 GoogleGoogleGoogle is an American technology company founded by Larry Page and Sergey Brin and incorporated in 1998. It became an Alphabet subsidiary in 2015. Its businesses include internet search, advertising, software platforms, cloud computing, and artificial intelligence.Open the full entry announced Ollama support in Firebase Genkit, its open source framework, at Google I/O 2024; on July 25 Ollama added tool support.⁠[4]

On May 15, 2025 Ollama introduced a new engine for multimodal models. On July 30 it released a new app for macOS and Windows for downloading and chatting with models, with drag-and-drop for text and PDF files and image input for models that support it; standalone CLI builds remained available on GitHub releases.⁠[4][9]

On September 19, 2025 Ollama introduced cloud models in preview, letting users run larger models on datacenter-grade hardware, starting with qwen3-coder:480b-cloud, gpt-oss:120b-cloud, gpt-oss:20b-cloud and deepseek-v3.1:671b-cloud. Cloud models require signing in to ollama.com, and the company said its cloud does not retain user data.⁠[10]

On March 30, 2026 Ollama began running on MLX on Apple Silicon in preview.⁠[4]

On July 9, 2026 Morgan and Chiang announced that Ollama had raised $88 million from Peter Fenton at Benchmark, Tomasz Tunguz at Theory Ventures and Alex Kolicich at 8VC, angels including Docker founder Solomon Hykes and ClickHouse CEO Aaron Katz, and investors including Y Combinator, Garage Capital, Pace Capital, 49 Palms and GTMFund. The company said Ollama served 8.9 million developers, was used by 85% of the Fortune 500, and had seen its cloud token volume more than double each month on average.⁠[1]

The latest round was a $65 million Series B led by Theory Ventures with existing backers including Benchmark and Y Combinator, intended for product development, computing power and key hires. The company then had 14 employees, with co-founder Jeff Morgan as CEO; he said it was organically adding about 100,000 users a week.⁠[2]

Ollama: Official website: https://ollama.com/ (opens in a new window).⁠[11]

X: Public account: https://x.com/ollama (opens in a new window).⁠[11]

LinkedInLinkedInLinkedIn is a social networking platform for professionals. It was founded in 2002 by Reid Hoffman and others, launched in 2003, and listed on the New York Stock Exchange in 2011; after Microsoft acquired it for approximately $26.2 billion in 2016, it became a wholly owned Microsoft subsidiary. Its revenue comes from membership subscriptions, advertising, and recruitment solutions.Open the full entry: Public profile: https://www.linkedin.com/company/ollama/ (opens in a new window).⁠[3]