Jonathan Ross
@JonathanRoss321
CEO & Founder @ Groq®, the Most Popular Fast Inference API | Creator of the TPU and LPU, Two of the Most Important AI Chips | Doubling 🌍's AI Compute by 2027
We built the region’s largest inference cluster in Saudi Arabia in 51 days and we just announced a $1.5B agreement for Groq to expand our advanced LPU-based AI inference infrastructure. Build fast.
On my girlfriends family vacation, at a lovely outdoor concert, but at @GroqInc we stay shipping.
.@JonathanRoss321 (the inventor and father of TPU) and I made this bet in 2017. @GroqInc is now the fastest inference solution in market today. Here are some lessons learned so far: - if we assume we get to Super Intelligence and then General Intelligence, the entire game…
$META CUSTOM AI CHIP OLYMPUS TARGETING $TSM 2NM NODE FOR 2027 MASS PRODUCTION TO CHALLENGE $NVDA RUBIN
Introducing Firecrawl Observer - an open source web monitor. Track any page or entire site with powerful change detection. Set custom intervals and receive instant webhook alerts on updates. Powered by @vercel, @Groq, @convex_dev, and more. Fork the example today 👇
Groq applauds @POTUS and the @WhiteHouse for releasing the AI Action Plan—a bold step to ensure American AI leadership worldwide. We’re proud to support the national effort to ensure U.S. AI technology is deployed and adopted worldwide. 🇺🇸 #AIActionPlan #AmericanAIStack
Groq is proud to join tomorrow’s "Winning the AI Race" event alongside leaders in the Admin, tech, manufacturing, and more. As the American inference leader, we believe that secure, accessible, affordable, and fast American-made AI infrastructure is essential to winning the AI…
Hill & Valley x All-In are hosting President @realDonaldTrump next week in DC for a day-long AI policy event. Hill & Valley Forum x All-In will host Winning the AI Race, a summit in Washington D.C. featuring a Keynote Address by President Donald J. Trump. This will be…
Pretty remarkable how fast the Kimi K2 ecosystem stood itself up — especially for a model with ~1T total parameters. That said, @GroqInc is in a league of its own on speed: >400 output tokens/sec, ~40x faster than Moonshot’s first-party API. There’s been a lot of debate about…
Kimi K2 Providers: Groq is serving Kimi K2 at >400 output tokens/s, 40X faster than Moonshot’s first-party API Congratulations to a number of providers to being quick to launch APIs for Kimi K2, including @GroqInc , @basetenco , @togethercompute, @FireworksAI_HQ, @parasail_io,…
OpenAI, Google, Anthropic, Microsoft, Groq. That’s the new top 5 for inference. Developers are choosing price-performance. Survey by @ArtificialAnlys.
1 week ago: Kimi K2 launches 72 hours later: We YOLO launch it on Groq Now: Thousands of devs are building with it Kimi K2, now on Groq: ✅ 1T parameters ✅ Full context ✅ Built for agents ✅ Unmatched price-performance Build Fast. Link in Comments.
I'm happy to inform you that you can now use Kimi K2 directly with Claude Code using my little claude-bridge tool via @GroqInc . Left -> Claude, Right -> Kimi K2 Claude still provides better answers and is cheaper. But K2 is quite fast (if the Groq servers aren't overloaded)
Congratulations @Kimi_Moonshot. What a week!
Agent Leaderboard v2 is here! > GPT-4.1 leads > Gemini-2.5-flash excels at tool selection > Kimi K2 is the top open-source model > Grok 4 falls short > Reasoning models lag behind > No single model dominates all domains More below:
🚨 BREAKING: @Kimi_Moonshot’s Kimi-K2 is now the #1 open model in the Arena! With over 3K community votes, it ranks #5 overall, overtaking DeepSeek as the top open model. Huge congrats to the Moonshot team on this impressive milestone! The leaderboard now features 7 different…
🚀 Hello, Kimi K2! Open-Source Agentic Model! 🔹 1T total / 32B active MoE model 🔹 SOTA on SWE Bench Verified, Tau2 & AceBench among open models 🔹Strong in coding and agentic tasks 🐤 Multimodal & thought-mode not supported for now With Kimi K2, advanced agentic intelligence…
Kimi K2 Providers: Groq is serving Kimi K2 at >400 output tokens/s, 40X faster than Moonshot’s first-party API Congratulations to a number of providers to being quick to launch APIs for Kimi K2, including @GroqInc , @basetenco , @togethercompute, @FireworksAI_HQ, @parasail_io,…
Kimi K2 + Groq is now available in anycoder for super fast vibe coding
Kimi K2 at 185 t/s (or even higher, nearly 220 in my short tests) is probably the best use of Groq to date, and can make K2 immediately more compelling than Sonnet 4. Impressive that they've managed to fit this 1T monster on their chips.
We’ve ben seeing a lot of demand for Kimi K2 on @GroqInc. Happy to say that it’s now available on the Groq API at 185 tokens per second, 6x faster than any other provider (AT FULL CONTEXT)
Kimi K2 running blazing fast on @GroqInc inside @cline. It's only going to get faster from here. Imagine full apps being built in minutes, and you as the developer get to choose from dozens of iterations and options at every step. That's the world we're moving towards.
Kimi K2 is now passing 200 tokens per second on OpenRouter Props to @GroqInc !
@GroqInc in a league of their own providing @Kimi_Moonshot K2 on @OpenRouterAI
Kimi K2 performs only slightly worse than grok 4 in terms of accuracy on @Stagehanddev, But has 7 times faster average inference speed. The battle of @GroqInc vs @grok
This is what 200 tokens/second looks like with Kimi K2 on @GroqInc For reference, Claude Sonnet-4 is usually delivered at ~60 TPS