Streaming responses with tool calling

Thinking

Secure Minions: private collaboration between Ollama and frontier models

Ollama's new app

OpenAI gpt-oss

Streaming responses with tool calling

Thinking

Secure Minions: private collaboration between Ollama and frontier models

Ollama's new app

OpenAI gpt-oss

Streaming responses with tool calling

Thinking

Secure Minions: private collaboration between Ollama and frontier models

Ollama's new app

OpenAI gpt-oss

Ollama v0.11.8 now enables flash attention by default on OpenAI's gpt-oss 20B and 120B models for systems that support it!

R to @ollama: Download new versions of Ollama: https://ollama.com/download Ollama's releases page: https://github.com/ollama/ollama/releases/tag/v0.11.8

RT by @ollama: Working on improvements for 16GB Macs, stay tuned 🫡

Ollama v0.11.7 is available with DeepSeek v3.1 support. You can run it locally with all its features like hybrid thinking. This works across Ollama's new app, CLI, API, and SDKs. Ollama's Turbo mode that's in preview has also been updated to support the model!

R to @ollama: Release page: https://github.com/ollama/ollama/releases/tag/v0.11.7 Download Ollama to give it a try: https://ollama.com/download

RT by @ollama: It was so incredible having a front-row seat at last night's gpt-oss meetup! Like web3, open-weight models re-localize computing, which is a prerequisite for a freer world. And also, they're just more fun. Major shoutout to @simon_mo_ @jmorgan & @dkundel for

RT by @ollama: I connected my Telegram bot to @ollama Turbo with DeepSeek v3.1. It's fast!