The Curious Engineer

All blogs / AI / ML

Ollama

ollama.com/blog

Ollama news, announcements, open model releases, product updates, tutorials, and technical guides for running AI models locally and in the cloud.

AI / MLDev tools / editors / IDEs

’23’24’25’26
Posts
63 from 1 Aug 2023 to 24 Oct 2026
Posting
monthly (23 in the last year)
Kind
project news
Feed
https://ollama.com/blog/rss.xml

2026 23

  1. Speech models in Ollama
  2. Clef is available on Ollama's cloud
  3. Reflection's Beam is freely available on Ollama for a limited time
  4. Run AI agents safely with Ollama and Fly.io
  5. Ollama now supports Jev-style decision models
  6. Ollama's transparent pricing
  7. Claude Desktop support with Ollama
  8. NVIDIA Nemotron 3.5 Lightning
  9. Muse Glimmer from Meta Superintelligence Labs is now available
  10. Ollama: all aboard open models
  11. Faster Gemma 4 on MLX with multi-token prediction
  12. Ollama's highest performance on Apple Silicon yet with MLX
  13. Improved performance and model support with GGUF
  14. NVIDIA Nemotron 3 Ultra
  15. OpenJarvis: a local-first personal AI is now available to run with Ollama
  16. Ollama is now powered by MLX on Apple Silicon in preview
  17. The simplest and fastest way to setup OpenClaw
  18. Subagents and web search in Claude Code
  19. OpenClaw
  20. ollama launch
  21. Image generation (experimental)
  22. Claude Code with Anthropic API compatibility
  23. OpenAI Codex with Ollama

2025 16

  1. OpenAI gpt-oss-safeguard
  2. MiniMax M2
  3. NVIDIA DGX Spark performance
  4. New coding models & integrations
  5. Qwen3-VL
  6. NVIDIA DGX Spark
  7. Web search
  8. New model scheduling
  9. Cloud models
  10. OpenAI gpt-oss
  11. Ollama's new app
  12. Secure Minions: private collaboration between Ollama and frontier models
  13. Thinking
  14. Streaming responses with tool calling
  15. Ollama's new engine for multimodal models
  16. Minions: where local and cloud LLMs meet

2024 18

  1. Structured outputs
  2. Ollama Python library 0.4 with function calling improvements
  3. Llama 3.2 Vision
  4. IBM Granite 3.0 models
  5. Llama 3.2 goes small and multimodal
  6. Reduce hallucinations with Bespoke-Minicheck
  7. Tool support
  8. Google Gemma 2
  9. An entirely open-source AI code assistant inside your editor
  10. Google announces Firebase Genkit with Ollama support
  11. Llama 3 is not very censored
  12. Llama 3
  13. Embedding models
  14. Ollama now supports AMD graphics cards
  15. Windows preview
  16. OpenAI compatibility
  17. Vision models
  18. Python & JavaScript Libraries

2023 6

  1. Building LLM-Powered Web Apps with Client-Side Technology
  2. Ollama is now available as an official Docker image
  3. Leveraging LLMs in your Obsidian Notes
  4. How to prompt Code Llama
  5. Run Code Llama locally
  6. Run Llama 2 uncensored locally