ollama (@ollama) / X

ollama

8,375 posts

ollama

@ollama

ollama.com

California, USA

github.com/ollama/ollama

Joined August 2023

Following

164.8K

Followers

Pinned
ollama
@ollama
Jun 16
🤯 GLM-5.2 is here — built for long-horizon coding and agentic tasks, now with a solid 1M-token context. The strongest open-source coding model yet! Available now on Ollama's cloud, hosted in the US on the latest @NVIDIAAI Blackwell datacenter GPUs. Privacy policy and zero
Z.ai
@Zai_org
Jun 16
Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong
194K
ollama reposted
Aaron Levie
@levie
8h
The fact that open weights models are being discussed credibly at this level of capability should be a huge update for many. The implications of open models getting to frontier performance ensures that you can always have sovereign AI, have the ability to post train for your
Marc Andreessen 🇺🇸
@pmarca
20h
Interesting. (Founder of Z.ai, creator of GLM AI models.)
76K
ollama reposted
Mat Velloso
@matvelloso
10h
All day using GLM 5.2. Didn't miss much. First open model that passes the bar as a daily driver. Things are not going to be the same. Damn, now I want to buy some serious hardware.
19K
ollama reposted
Jeremy Howard
@jeremyphoward
12h
Wow. @Zai_org GLM 5.2 is a marvel! It is *at least* as good as Opus 4.8 and GPT 5.5. It's super fast, inexpensive, and not too verbose. It responds with nuance and judgement, & handles long context VERY well. I've never experienced an open weights model like this before.
392K
ollama
@ollama
14h
GLM 5.2 on Ollama's cloud just doubled GPU capacity to handle the volume of usage! This is all US based, and running on NVIDIA B300 Blackwell GPUs. We believe privacy matters! Let's go open models! ❤️
135K
ollama
@ollama
18h
Let's go open models! ❤️
Cohere
@cohere
18h
Replying to @cohere
North Mini Code is now supported on @ollama. Now, run our model locally, and use it with Codex, OpenClaw, and more. Download it here: cohere.link/SVwVbGZ
36K
ollama reposted
Alberto Nunez-Garcia
@Alberto8793
Jun 18
Replying to @HarryStuck77 @ivanfioravanti and 2 others
For GLM only? @ollama those fluffy little guys have captured my heart
4.3K
ollama reposted
Tibo
@thsottiaux
Jun 17
Reminder that you can use the Codex App, CLI and SDK with any open source model, not just with OpenAI models.
Advanced Configuration – Codex | OpenAI Developers
From developers.openai.com
2M
ollama
@ollama
Jun 17
let's go open models! ❤️
Hassan
@nutlope
Jun 17
This model is insane at design. I asked GLM 5.2 (left) and Opus 4.8 (right) to build me a landing page and you can't even tell the difference. GLM cost $0.06 while opus cost $0.49. More than 6x cheaper while being faster + more token efficient. Another win for open source AI.
00:00
66K
ollama
@ollama
Jun 17
let's go open models! ❤️
nick vasilescu
@nickvasiles
Jun 16
GLM 5.2 is genuinely so impressive! We finally have SOTA level of intelligence at a fraction of the cost And I genuinely prefer the outputs & personality of GLM 5.2 as opposed to GPT 5.5 We’ll be using it in Hermes for myself and for clients
38K
ollama
@ollama
Jun 17
You can use GLM-5.2 and Kimi-K2.7-Code in Codex with Ollama! ollama launch codex ollama launch codex-app
Tibo
@thsottiaux
Jun 17
Reminder that you can use the Codex App, CLI and SDK with any open source model, not just with OpenAI models. developers.openai.com/codex/config-a…
78K
ollama reposted
Lou
@louszbd
Jun 16
Replying to @ollama @NVIDIAAI and @Zai_org
9.9K
ollama reposted
Ankit Gupta
@agupta
Jun 16
Exo 0.14.0 is out today with Day-0 support for GLM 5.2 (from @Zai_org) and @opencode harness support. GLM is the first open model that achieves comparable performance to Opus in my internal eval, and runs at approximately the same speed on @ollama cloud. it's now my default
Ankit Gupta
@agupta
Mar 30
Fun update: I got tired of disliking every email client I’ve ever used and built my own. It’s called Exo (for exoskeleton). It’s Claude Code for my inbox. It manages my inbox for me, and it’s open source. Link to repo + some notable features in thread!
57K