Ollama
6stories this week
16last 30 days
27all time
Timeline
- Oct 11, 2026 · Opinion / analysis · 1 sourceI built GOAT’d Text Generator 🐐 - generate prompts directly in ComfyUII made a custom node that brings cloud and local LLMs into your ComfyUI workflows.
- Oct 11, 2026 · Open-source release · 1 sourceollama/ollama v0.40.3
- Oct 10, 2026 · Opinion / analysis · 1 sourceNace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores Options, Not TextNace.AI has open-sourced Drex 1.5, a 9B decision model for agents and backend workflows.
- Oct 9, 2026 · Model release · 2 sourcesConwayResearch/Underdog-Saluki-27B-1.0ConwayResearch published the model Underdog-Saluki-27B-1.0 on Hugging Face.
- Oct 8, 2026 · Open-source release · 1 sourceollama/ollama v0.40.2Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp.
- Oct 7, 2026 · Open-source release · 1 sourceollama/ollama v0.40.1
- Oct 3, 2026 · Model release · 1 source[AINews] not much happened todayAINews’ website lets you search all past issues.
- Oct 1, 2026 · Opinion / analysis · 1 sourceShow HN: Breadcrumb, record everything on your mac + context manager for AIBreadcrumb records everything you do on your Mac (screen + meetings + AI transcripts + what you and your AI decided) and turns it into memory your AI can search.
- Sep 29, 2026 · Open-source release · 1 sourceollama/ollama v0.35.1Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it.
- Sep 29, 2026 · Opinion / analysis · 1 sourceOllama now supports Jev-style decision modelsOllama now supports decision models, based on TypeSafe's Jev API for fast, typed decisions.
- Sep 28, 2026 · Open-source release · 1 sourceollama/ollama v0.35.0Decision models return choices, probabilities, and scores instead of text.
- Sep 25, 2026 · Open-source release · 1 sourceollama/ollama v0.40.0Models run on MLX on Apple Silicon by default
- Sep 23, 2026 · Open-source release · 1 sourceollama/ollama v0.34.4Qwen 3.8 prompt processing is faster on Apple Silicon.
- Sep 19, 2026 · Open-source release · 1 sourceollama/ollama v0.34.3GET /api/show now advertises each model's thinking controls and default:
- Sep 15, 2026 · Open-source release · 1 sourceollama/ollama v0.34.2Added first-run setup when running ollama, with options to sign in or continue locally.
- Sep 14, 2026 · Open-source release · 1 sourceollama/ollama v0.34.1GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization.
- Sep 5, 2026 · Open-source release · 1 sourceollama/ollama v0.34.0Use Ollama models in ChatGPT Desktop
- Sep 2, 2026 · Open-source release · 1 sourceollama/ollama v0.33.3gemma4 now supports images and audio on MLX engine
- Aug 27, 2026 · Open-source release · 1 sourceollama/ollama v0.33.2Ollama's app now follows the system appearance again, restoring dark mode support
- Aug 26, 2026 · Open-source release · 1 sourceollama/ollama v0.33.1mlxrunner: avoid Metal GPU timeouts when loading models from slow storage
- Aug 21, 2026 · Open-source release · 1 sourceollama/ollama v0.33.0Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
- Aug 19, 2026 · Open-source release · 1 sourceollama/ollama v0.32.15New desktop onboarding flow on first launch
- Aug 15, 2026 · Open-source release · 1 sourceollama/ollama v0.32.14llm: transcode WebP images for llama-server
- Aug 14, 2026 · Open-source release · 1 sourceollama/ollama v0.32.13
- Aug 14, 2026 · Open-source release · 1 sourceollama/ollama v0.32.12Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
- Aug 14, 2026 · Open-source release · 1 sourceollama/ollama v0.32.11The OpenAI-compatible Responses API now supports web search
- Jun 9, 2026 · Model release · 1 sourceIntroducing Gemma 4 12B: a unified, encoder-free multimodal modelIntroducing Gemma 4 12B: a unified, encoder-free multimodal model