We've been limited to Claude Desktop and IDEs like Cursor for MCP... until now. ⚡️ We shipped Groq Desktop, a new MCP host that's insanely fast. You can now give models like Llama 4 Scout and Qwen QwQ 32B the ability to instantly read PDFs, connect to Slack, and so much more.

and my last stop for @groqinc is @nvidia 💚

some closing thoughts as i reflect on 2025: in just 52 weeks, we've made breakthroughs in model intelligence and open-source went from catching up to leading -- so many labs, old and new, dropping releases every other week. models uploaded to huggingface nearly doubled year

meta’s 2026 revival has commenced

this aged well

had early access over the past few days and all i'll say for now is try m2.1 with @droid.

my sister: “move out of the way tsx” me, a python user: for real

tbh claude i prefer this over "you're absolutely right!"

i've personally been using @MiniMax__AI's minimax-m2 for coding for the past 2 weeks and it's a gem. keep your eyes open for open models. 🤗

we've been heads down @groqinc and you'll see why soon

ICYMI: We just reworked ALL our @GroqInc docs with better organization and more examples, especially around tool calling! Tool calling can be tricky, especially when deciding between built-in tools, remote tools / MCP, or local tools. We've got a helpful guide to you out!

the people yearn for fast inference on coding models… stay tuned

yk you’re old when this is how you find out about spotify wrapped

The days of manually searching through Google Workspace are coming to an end - I'll personally be speaking to mine by integrating this into a voice agent with @pipecat_ai. 😺 As always, LMK if you want a tutorial + any feedback. Get started here:

ICYMI: We shipped MCP Connector support for easy read-only access to your Gmail, Google Calendar, and Google Drive via Groq API. 🚀 Our (server-)side = lower latency, zero‑ops integration. Your side = just manage/pass in your OAuth token.

billions of dollars vs. 🐋 choose your fighter

I also think @Replit , @vercel v0, @Lovable and the rest should consider using @cerebras and @GroqInc for MVPs and prototypes. It's very hard to edit and augment when you have to wait 2-3 min for the agent and it may/may not do what you want. Also, consider the price of

someone stopped me in new haven ct yesterday: “wait aren’t you from groq” have i achieved micro celebrity status

Let’s build agents that actually do something. 🔭🔧🧪 Join the hackathon with @GroqInc, @Docker, and @e2b where you can give agents 200+ tools via MCPs installed in the sandbox environment. 🌏 Online: Friday Nov 21 🌁 Offline: Saturday Nov 22, San Francisco 👇 Signup via

me when claude creates bloated markdown files detailing changes

🍕 Melbourne Data Eng Meetup: Nov 20, 5–7PM 👉