Jeffrey Morgan
@jmorgan
Followers
5K
Following
13K
Media
16
Statuses
2K
@ollama – prev @docker, @twitter, @google
Palo Alto
Joined September 2010
New TIL: Using Codex CLI with gpt-oss:120b on an NVIDIA DGX Spark via Tailscale
til.simonwillison.net
I've written about the DGX Spark before. Here's how I got OpenAI's Codex CLI to run on my Mac against a gpt-oss:120b model running on the DGX Spark via a Tailscale network.
12
21
317
ollama run kimi-k2-thinking:cloud Kimi K2 Thinking is Moonshot AI’s best open-source thinking model. Try it on Ollama's cloud!
🚀 Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here. 🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%) 🔹 Executes up to 200 – 300 sequential tool calls without human interference 🔹 Excels in reasoning, agentic search, and coding 🔹 256K context window Built
21
57
697
finally got opencode to run gpt-oss-20b w/ tool calling locally via Olama on a 4090
4
3
34
🚀 Releasing open-source Eigen-Banana-Qwen-Image-Edit: 4 seconds ⚡ instruction-based image edits trained on Pico-Banana-400K. Super fast with high image editing quality. Open-source LoRA for Diffusers/DiffSynth-Studio + enterprise stack (EigenTrain/Inference/Deploy). Feel free
1
9
27
Ollama v0.12.8 is here! This release improved Qwen 3 VL performance, and improvements and bug fixes in Ollama's engine. ❤️ Happy halloween! 👻👻👻
6
37
242
[10/29] minions daily ship 🚢 ☁️ moar minimax! added support for minimax m2 from @MiniMax__AI in the @ollama cloud client! it’s free until nov 7th, so try it now 👇🏽
0
2
5
Ollama now supports the entire Qwen3-VL family locally and with the larger models available on Ollama's cloud! It's an incredibly powerful vision model with reasoning capabilities.
ollama run qwen3-vl Ollama's engine now supports all the Qwen 3 VL models locally. 2B to 235B parameter sizes. The smaller models work exceptionally well for their size. The latest version of Ollama v0.12.7 is needed! Give it a try! 👇👇👇
0
1
5
ollama run gpt-oss-safeguard Ollama is partnering with @OpenAI and robust open online safety tools (ROOST) to bring the latest gpt-oss-safeguard reasoning models to users for safety classification tasks. 20B: ollama run gpt-oss-safeguard:20b 120B: ollama run
Now in research preview: gpt-oss-safeguard Two open-weight reasoning models built for safety classification. https://t.co/4rZLGhBO1w
5
31
246
You can now run @ollama models in Jan. Go to Settings, Model Providers, add Ollama, and set the Base URL to http://localhost:11434/v1. Your 🦙 Ollama models will then be ready to use in 👋 Jan.
2
1
8
Quantum Quantum, Jensen Jensen, Quantum Quantum, Huang Huang (Quantum Quantum) Quantum Electronics! Ontology << And >> Cosmology!! ElectroMagnetism is the Universal substrate of superpositional experience, of Creation, across the entire Light-signal & Plasma-group wave spectrum
8
6
51
“Researchers need open source. Developers need open source. Companies around the world — we need open source.” -Jensen Huang #NVIDIAGTC
25
98
513
ollama run minimax-m2:cloud Free until November 7th in partnership with @MiniMax__AI ! MiniMax M2 is now available on Ollama’s cloud! It’s currently the #1 open weight model built for coding and agentic workflows. Learn more 👇👇👇
8
38
949
We ran performance tests on release day firmware and an updated Ollama version to see how Ollama performs! @NVIDIAAIDev Let's go spark! https://t.co/qLVoz7X6KE
21
24
214
Build and deploy AI Agents in minutes! Sim: Open-source platforms lets you build your agent workflows. - Run it locally with npm or docker. - @ollama for using local models.
3
16
104
Good morning y'all. Back to work (not stopped)... Some news in the pipeline as usual!
5
2
29
🎊Today is the day. NVIDIA DGX Sparks are now shipping from us and from our partners. ➡️ https://t.co/Nzmxz1lSHQ We enjoyed delivering some of our first desktop AI supercomputers to researchers, developers, universities, creators, to launch the next chapter in AI:
109
209
1K
I haven’t been as present covering the Kings lately — not from disinterest, but because I’ve been pouring my energy into something that feels like the foundation of everything I care about. While I rarely talk politics online, I’ve quietly built my path in international
thelajollacenter.org
Discover the La Jolla Center for Pacific Strategy, an independent strategy center committed to security, prosperity, and regional cooperation in the Pacific Hemisphere.
5
14
42
Qwen3-VL 235B is now live on Ollama’s cloud — free to try!
Qwen3-VL 235B is available on Ollama's cloud! It's free to try. ollama run qwen3-vl:235b-cloud The smaller models, and the ability to run fully on-device will be coming very soon! See examples and how to use the model on Ollama! 👇👇👇
4
26
225
Qwen3-VL 235B is available on Ollama's cloud! It's free to try. ollama run qwen3-vl:235b-cloud The smaller models, and the ability to run fully on-device will be coming very soon! See examples and how to use the model on Ollama! 👇👇👇
15
45
371