Introducing our first set of Llama 4 models!
We’ve been hard at work doing a complete re-design of the Llama series. I’m so excited to share it with the world today and mark another major milestone for the Llama herd as we release the *first* open source models in the Llama 4 collection 🦙. Here are some highlights:
📌 The Llama series have been re-designed to use state of the art mixture-of-experts (MoE) architecture and natively trained with multimodality. We’re dropping Llama 4 Scout & Llama 4 Maverick, and previewing Llama 4 Behemoth.
📌 Llama 4 Scout is highest performing small model with 17B activated parameters with 16 experts. It’s crazy fast, natively multimodal, and very smart. It achieves an industry leading 10M+ token context window and can also run on a single GPU!
📌 Llama 4 Maverick is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding �� at less than half the active parameters. It offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena. It can also run on a single host!
📌 Previewing Llama 4 Behemoth, our most powerful model yet and among the world’s smartest LLMs. Llama 4 Behemoth outperforms GPT4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on several STEM benchmarks. Llama 4 Behemoth is still training, and we’re excited to share more details about it even while it’s still in flight.
A big thanks to all of our launch partners (full list in blog) for helping us bring Llama 4 to developers everywhere including @huggingface, @togethercompute, @SnowflakeDB, @ollama, @databricks and many others👏 This is just the start, we have more models coming and the team is really cooking – look out for Llama 4 Reasoning 😉
A few weeks ago, we celebrated Llama being downloaded over 1 billion times. Llama 4 demonstrates our long-term commitment to open source AI, the entire open source AI community, and our unwavering belief that open systems will produce the best small, mid-size and soon frontier models. Llama would be nothing without the global open source AI community & we are so ready to begin this next chapter with you. 🦙
Read more about the release here: https://t.co/7mbK3uggjO, and try it in our products today.
"I think children give you the unique opportunity to genuinely love something more than you love yourself. And I think that is really important for being happy because the moment you love something more than you love yourself, you're no longer self-obsessed."
@naval
My main use case for chat gpt now is to verbally ask questions about random things my kids are curious about such as: why did Korean brands become famous? or when did the Europeans stop throwing poo into the street?
I find the comparisons to knowledge in ancient times are always apt when it comes to ai. "The ancient Sumerians and Egyptians were creating medicines from salicylate-rich plants such as willows long before humans understood why such chemicals reduce pain and inflammation."
Kalo kemarin NYSE, sekarang Nasdaq yang nyelametin, dan di Times Square. Kelihatannya keren banget ya, padahal dipikir-pikir, gitu weh dipajang di pengkolan.
I love these two charts.
L: After Deep Blue beat Kasparov, the number of Super Grandmasters increased dramatically.
r: After AlphaGo beat Lee Sedol, the quality and novelty of human Go players' moves spiked.
Human minds aren't static. They improve and evolve.
@cz_binance Impeccable timing. Pure serendipity or planned execution? HK central bank urging traditional banks to “endeavour to support virtual asset service providers (VASPs)“ while the US Is cracking down on crypto.
We also asked which foreign pop cultures people most enjoyed, trying to see how much soft power other countries have in Indonesia. This was one of the few measures where India came out favourably, perhaps reflecting the popularity of Bollywood in Indonesia 10/
@lutfithe13th Wah makasih, tapi yg membuat penasaran apakah Kamboja
dan Filipina lebih baik secara talenta dan planning? Kalau Singapore dan Vietnam maklumlah.
Thailand, Vietnam, India and Cambodia have emerged as early winners this year from US moves to secure its semiconductor supply chain https://t.co/6NDJbdSTxL via @technology