ollama

Ollama now supports Codex app! To try it, update to the latest Ollama 0.24, and run: ollama launch codex-app Select an open model to use with Codex app! 🧵

@lillian_ma_ @NVIDIA_AI_PC @NousResearch build.nvidia.com/spark/hermes-a…

@NVIDIA_AI_PC @NousResearch @ollama Hey a friendly reminder this link is not working @ollama build.nvidia.com/spark/ollama

Run @NousResearch's Hermes Agent fully locally on DGX Spark. 🚀 Our newest playbook shows you how to get set up via @Ollama step by step. 👇

@nvidia @AnthropicAI @OpenAI @SpaceX @OracleCloud Super cool! 😎

NVIDIA’s Ian Buck hand-delivered the first-ever NVIDIA Vera CPUs to our partners @AnthropicAI, @OpenAI, @SpaceX, and @OracleCloud. 🎉 Vera is NVIDIA's first custom CPU, purpose-built for the age of agentic AI. This is just the beginning. The road to Vera-powered systems starts here. Thank you to our partners for being on this journey with us. The best is yet to come. 💚

@abytenext Totally okay!

Hey @ollama can I have two cloud accounts ? One for work (max) and another one personal (free or max) ? Or that’s against your TOS and will get me banned?

@xeophon @arcee_ai Open > closed

@NVIDIA_AI_PC @NousResearch 🚀🚀🚀

@ollama 🚀

@NVIDIAAI ❤️❤️❤️

We just added significantly more NVIDIA Blackwell GPUs to better serve GLM-5.1 model on Ollama's cloud. We have been adding more GPUs daily for all the other models. Claude Code: ollama launch claude --model glm-5.1:cloud Codex App: ollama launch codex-app Hermes Agent: ollama launch hermes --model glm-5.1:cloud Run the model: ollama run glm-5.1:cloud

@emanperez28 if you are using ollama models you won't touch token usage for codex

@ollama So will this solely use the agentic models from ollama, and won’t touch my token usage for codex?

Ollama now supports Codex app! To try it, update to the latest Ollama 0.24, and run: ollama launch codex-app Select an open model to use with Codex app! 🧵

@krapstarr Improving it! ❤️🚀

@ollama Great, please improve deepseek

Model page: ollama.com/library/glm-5.1

@MichaelGannotti @tonysimons_ ❤️❤️❤️ Thank you for bearing with us!!

Turns out it was flipping them all to Deepseek and with asking all agents also flipped heartbeats from local inference to deepseek. Thankfully the folks at @ollama were gracious and helped out with some great customer support. Back running. Heartbeats all local now again and moved all agents to combo of Kimi K2.6 and GLM5.1

Wait what??? I just upped to 5X and I am still used up this whole thing is starting to get ridiculous. What the hell have my OpenClaw been up to. Shut everything down. Looks like @ollama doesn’t have the usage capacity I need and I can’t afford any more. Pretty frustrated. Between work and now this.

@ErRahul337 the same benefits of the codex app - but now using open models! Some people prefer the terminal, and that works too.

@ollama What benifits we will get this support, I am running codex on terminal

Restore to existing Codex experience without any effects: ollama launch codex-app --restore

Some models to try with Codex: kimi-k2.6:cloud (with vision support) glm-5.1:cloud If you don't yet have a paid subscription with Ollama's cloud, choose a model that supports reliable tool calling: nemotron-3-super:cloud gemma4:31b:cloud qwen3.6

@ZixuanLi_ @aiDotEngineer 😂

See you in Singapore. BTW, I'm starting to look more and more like our logo.