🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

[6/25] minions daily ship 🚢 🔨 ollama ❤️ mcp! we updated our ollama client so that you can integrate ollama tool calling with any Anthropic mcp server and….celebrating 1k ⭐’s on github! ty for all the support 😊

Serverless Gemma 3n with @Ollama and Cloud Run in two commands: $ gcloud run deploy --image ollama/ollama --port 11434 --gpu 1 $ OLLAMA_HOST=[...] ollama run gemma3n

[6/29] minions daily ship 🚢 🧑🏽‍🦰 character chat app! saw that role-play apps are taking off on OpenRouter — so we made it local-first. we 🚢’d a character chat app: ☁️ lms spin up the persona, local gemma3n (via ollama) drives the conversation on-device give it a whirl →

It’s easy to fine-tune small models w/ RL to outperform foundation models on vertical tasks. We’re open sourcing Osmosis-Apply-1.7B: a small model that merges code (similar to Cursor’s instant apply) better than foundation models. Links to download and try out the model below!

happy July 4th! Ollama is celebrating by building.

[7/4] minions daily ship 🚢 📖 story time! happy 4th 🇺🇸 — shipping a fun one today: an app where a remote lm and local ollama lm team up to write children’s stories! image gen powered by the <12b param flux model from Black Forest Labs check it out → apps/minion-story-teller

The ollama inference pod.

Do you believe in local LLMs?

Hot tip for anyone doing AI dev: Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API The smaller models are fast and good enough to work on new features or debug streaming

minions will be there to celebrate ollama's birthday!

Ladies and gentleman a fully functional Next.js app you can test locally, powered by Genkit framework + ollama and local models. Works with various vision models. I tested it with LLaVA and Gemma 3 already, good results. Source code to follow.

.ollama working to bring more updates...