(Fun fact: the distillation paper was rejected from NeurIPS 2014 because it was "unlikely to have significant impact").

@essential_ai @pcmonk @ashVaswani This model works with pre-release version of Ollama v0.13.3. We are releasing an updated Ollama version soon. Pre-release version is available here: https://t.co/g0vbrgeJDT

Model page: https://t.co/H9egXNvwWd

.@essential_ai's rnj-1 model is now on Ollama! ollama run rnj-1 8B parameter, open-weight dense model trained from scratch. The model is optimized for code and STEM with capabilities on par with other state of the art open-weight models. Let's go! 🚀🚀🚀

Model page: https://t.co/cHlay4cere

ollama run deepseek-v3.2:cloud DeepSeek v3.2 is now on Ollama's cloud! DeepSeek v3.2 on Ollama's cloud can have thinking enabled and disabled. Give it a try. It's free to get started!

Sync your @ollama local models!

Model page https://t.co/iUrquiUcoS

Qwen 3 Next is now on Ollama! ollama run qwen3-next

Yesterday was my first time doing a live demo at NeurIPS, and it happened at the @ollama booth. Super excited that the idea we hacked together in just a few hours actually worked so well 🎉 We showed a hybrid Ollama @ollama × SGLang @lmsysorg setup: Run local LLMs through the

Support for running Mistral Large 3 locally will be available in Ollama soon.

https://t.co/DJfUqE0RdP

Run Mistral Large 3 on Ollama's cloud: ollama run mistral-large-3:675b-cloud

Ministral 3 is now also available on Ollama's cloud: 14B: ollama run ministral-3:14b-cloud 8B: ollama run ministral-3:8b-cloud 3B: ollama run ministral-3:3b-cloud https://t.co/pi5FywAD7Q

Mistral 3 is now available on Ollama v0.13.1 (currently in pre-release on GitHub). 14B: ollama run ministral-3:14b 8B: ollama run ministral-3:8b 3B: ollama run ministral-3:3b Please update to the latest Ollama.

https://t.co/pi5FywAD7Q

Mistral 3 is now available on Ollama v0.13.1 (currently in pre-release on GitHub). 14B: ollama run ministral-3:14b 8B: ollama run ministral-3:8b 3B: ollama run ministral-3:3b Please update to the latest Ollama.

[11/27] minions daily ship 🚢 🦃 cogito-2.1! grateful for 🇺🇸 os lms, esp @DeepCogito's latest drop. try out their new 671b param model, powered by the @ollama ☁️

1/2 I'll be at NeurIPS 2025 next week with @trycua and @ollama. If you're working on real-world evaluations, post-training excellence, or building general AI agents that can actually use computers, come say hi. I'll be at the Ollama booth demoing our latest playground interface!

Uh oh. 🍔