Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

When will AI personal assistants be fast enough to be useful? Using Qwen 3.8 27B on Cerebras at ~1,500 tokens/sec, we made an AI personal assistant 19x faster than a suite of other AI personal assistants - Grok Bot, Meta Muse, and Claude Cowork - on the same dinner... show more

Cerebras

78,432 subscribers

27,910 views • 8 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Comments

Cerebras8 days ago

Read the full blog by @MilksandMatcha:

Tapa Ghosh8 days ago

Seems slower than TPU?

Dominik Gstöhl8 days ago

using it with @trycua - booooom

Talk AI Today8 days ago

Always old model 😂 cerebras you suck now for developers … continue to sell to OpenAI your hardware

ShadowAguy8 days ago

The useful number is probably reservations confirmed per minute, not tokens per second. How much of the run was model time versus browser and booking-tool latency?

selene8 days ago

Suck

EDDY VU8 days ago

At 1,500 tokens per second, does the bottleneck completely shift over to external API calls now?

Mega Kilo8 days ago

Yes but 128K context. A few rounds of agentic actions would use it up. When 256K context?

무자본진리8 days ago

내부자 매도가 너무 많다

Clint Fix8 days ago

Would be awesome if you brought Gemma back

Claudio Aldana8 days ago

yeah but is cerebras used in Ultrafast?, that would be a start at least

Yashas8 days ago

@MilksandMatcha Hey, I'm working on something in personal AI... Wanna partner again?👀

selene8 days ago

Bro spends 24/7 hyping his own stock on here, yet OpenAI didn’t even bother using your chips for their latest model. Truly embarrassing."

Sathya8 days ago

Please bring more models.

Matt Albrizio8 days ago

Ok but release it so we can use it.

Related Videos

I compared every single AI personal assistant on the same task: Grok Bot: 7 min 40 sec Meta Muse: 4 min 36 sec Instinct: 14 min + Claude Cowork: 6 min 25 sec Human (me) : 37 sec Cerebras: 22 sec

I compared every single AI personal assistant on the same task: Grok Bot: 7 min 40 sec Meta Muse: 4 min 36 sec Instinct: 14 min + Claude Cowork: 6 min 25 sec Human (me) : 37 sec Cerebras: 22 sec

Sarah Chieng

217,662 views • 12 days ago

We built Money Agent, a personal finance assistant powered by Qwen 3.8 27B on Cerebras. Now you can turn a home-buying question into a real-time conversation, then into a financial goal, faster.

We built Money Agent, a personal finance assistant powered by Qwen 3.8 27B on Cerebras. Now you can turn a home-buying question into a real-time conversation, then into a financial goal, faster.

Cerebras

107,457 views • 19 days ago

🎂 Cerebras Inference turns 1! 🚀 Let's break it down: - 6x faster than when we launched — From Meta Llama to Qwen 3 to OpenAI OSS, models running on Cerebras deliver 𝟯,𝟬𝟬𝟬+ 𝘁𝗼𝗸𝗲𝗻𝘀/𝘀𝗲𝗰 - Our inference powers the best AI natives, global enterprises, and developers including Meta, IBM , AlphaSense, Docker, GSK , Mayo Clinic, Core42, Vercel and more - Largest model served: ~half a trillion parameters, 7x bigger than launch - #1 provider of tokens on Hugging Face 🤗 - Serving billions of tokens per day on - The leading code gen inference provider, powering AI developers with Cline and Windsurf (retired) We’re just getting started… but couldn’t have done Year 1 without YOU. Build on, builders. ❤️‍🔥

🎂 Cerebras Inference turns 1! 🚀 Let's break it down: - 6x faster than when we launched — From Meta Llama to Qwen 3 to OpenAI OSS, models running on Cerebras deliver 𝟯,𝟬𝟬𝟬+ 𝘁𝗼𝗸𝗲𝗻𝘀/𝘀𝗲𝗰 - Our inference powers the best AI natives, global enterprises, and developers including Meta, IBM , AlphaSense, Docker, GSK , Mayo Clinic, Core42, Vercel and more - Largest model served: ~half a trillion parameters, 7x bigger than launch - #1 provider of tokens on Hugging Face 🤗 - Serving billions of tokens per day on - The leading code gen inference provider, powering AI developers with Cline and Windsurf (retired) We’re just getting started… but couldn’t have done Year 1 without YOU. Build on, builders. ❤️‍🔥

Cerebras

35,218 views • 1 year ago

1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure. try it now:

1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure. try it now:

Alexandr Wang

12,756,933 views • 29 days ago

We're excited to collaborate with Upstage, one of Korea's leading AI companies. Upstage's Solar 31B is now running on Cerebras at up to 2,000 tokens/sec. Watch Solar 31B complete a deep research query across 246 sources...how much faster do you think it is?

We're excited to collaborate with Upstage, one of Korea's leading AI companies. Upstage's Solar 31B is now running on Cerebras at up to 2,000 tokens/sec. Watch Solar 31B complete a deep research query across 246 sources...how much faster do you think it is?

Cerebras

39,293 views • 2 months ago

Imagine a future where you have truly personal and proactive assistants on the best personal AI devices ever - your MacBooks. With MLX, that future is already here. Apple Silicon makes local AI genuinely powerful. We hosted MLX India’s first community meet-up on May 3rd. And here’s what people had to say.

Imagine a future where you have truly personal and proactive assistants on the best personal AI devices ever - your MacBooks. With MLX, that future is already here. Apple Silicon makes local AI genuinely powerful. We hosted MLX India’s first community meet-up on May 3rd. And here’s what people had to say.

sabesh 📟

20,616 views • 4 months ago

We have built one of the smartest financial assistants in the world. Silvia leverages state of the art AI models to give you insights on your personal investment portfolio. Wicked smart. Lightning fast. Completely free. Sign up here:

We have built one of the smartest financial assistants in the world. Silvia leverages state of the art AI models to give you insights on your personal investment portfolio. Wicked smart. Lightning fast. Completely free. Sign up here:

Anthony Pompliano 🌪

105,909 views • 11 months ago

How to master delegation w/ Jonathan Swanson Jonathan Swanson is the Founder of Athena, which pairs ambitious people with exceptional assistants. He's an expert on using delegation to work more effectively. He joined a16z GP Erik Torenberg for a deep dive on delegation, assistants, productivity, and more. They cover: - How delegation turns into leverage - What Jonathan learned from watching assistants in the West Wing - Why holding onto things you think you can do faster is the cardinal sin of delegation - The case for having many personal assistants - How to delegate by algorithm, not task - How AI will slot into people's productivity systems and more. Jonathan Swanson Erik Torenberg

How to master delegation w/ Jonathan Swanson Jonathan Swanson is the Founder of Athena, which pairs ambitious people with exceptional assistants. He's an expert on using delegation to work more effectively. He joined a16z GP Erik Torenberg for a deep dive on delegation, assistants, productivity, and more. They cover: - How delegation turns into leverage - What Jonathan learned from watching assistants in the West Wing - Why holding onto things you think you can do faster is the cardinal sin of delegation - The case for having many personal assistants - How to delegate by algorithm, not task - How AI will slot into people's productivity systems and more. Jonathan Swanson Erik Torenberg

a16z

64,252 views • 10 months ago

Qwen3.8-27B is now live at Cerebras speed. The dense, open-weight model from Qwen scores 34 on the Artificial Analysis Intelligence Index—making it comparable to models such as GPT-5.6 Luna, DeepseekV4 Pro, and Claude Sonnet 4.6.

Qwen3.8-27B is now live at Cerebras speed. The dense, open-weight model from Qwen scores 34 on the Artificial Analysis Intelligence Index—making it comparable to models such as GPT-5.6 Luna, DeepseekV4 Pro, and Claude Sonnet 4.6.

Cerebras

292,623 views • 26 days ago

🚨 Big news! Cerebras is launching six new AI data centers across North America & Europe. This expands our capacity to 40M+ tokens/sec, making Cerebras the first hyperscale cloud for high-speed AI inference. Read more:

🚨 Big news! Cerebras is launching six new AI data centers across North America & Europe. This expands our capacity to 40M+ tokens/sec, making Cerebras the first hyperscale cloud for high-speed AI inference. Read more:

Cerebras

27,477 views • 1 year ago

📣 ANNOUNCEMENT DAY AT CEREBRAS 📣 Today, we are thrilled to share some of the biggest announcements in our company’s history. 📢 Cerebras announces CS-3, the world’s fastest AI Chip with a whopping 4 trillion transistors 📢 Cerebras selects Qualcomm to deliver unprecedented performance in AI Inference 📢 Cerebras and G42 break ground on Condor Galaxy 3, an 8 exaFLOPs AI Supercomputer Read all about it! 📰 CS-3 Press Release: 📰 Cerebras + Qualcomm Press Release: 📰 Condor Galaxy 3 Press Release: #AI #Supercomputer #ExaFLOPs #ML #Training #Inference

📣 ANNOUNCEMENT DAY AT CEREBRAS 📣 Today, we are thrilled to share some of the biggest announcements in our company’s history. 📢 Cerebras announces CS-3, the world’s fastest AI Chip with a whopping 4 trillion transistors 📢 Cerebras selects Qualcomm to deliver unprecedented performance in AI Inference 📢 Cerebras and G42 break ground on Condor Galaxy 3, an 8 exaFLOPs AI Supercomputer Read all about it! 📰 CS-3 Press Release: 📰 Cerebras + Qualcomm Press Release: 📰 Condor Galaxy 3 Press Release: #AI #Supercomputer #ExaFLOPs #ML #Training #Inference

Cerebras

128,669 views • 2 years ago

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.

Cerebras

1,291,350 views • 1 month ago

Cerebras and Mayo Clinic are proud to announce a new state-of-the-art foundation model for genomics. The breakthrough was made possible by combining Mayo Clinic's extensive patient data with the Cerebras AI platform, training on over a trillion tokens to create complex genomic models that can guide personalized treatment decisions. Read more:

Cerebras and Mayo Clinic are proud to announce a new state-of-the-art foundation model for genomics. The breakthrough was made possible by combining Mayo Clinic's extensive patient data with the Cerebras AI platform, training on over a trillion tokens to create complex genomic models that can guide personalized treatment decisions. Read more:

Cerebras

44,578 views • 1 year ago

🧵1/7 💎 $wBAI – an AI bluechip 💎 Balance AI Network is a platform where AI is cooperative, transparent and secure. The goal is to create your personal AI trading assistant, watch the video and you will immediately understand what this will do! This #AI assistant isn't just a tool; it's your financial guide, providing insights on investments with precision. It's data-driven decision-making made personal! This is why big names in the #Crypto space are jumping on this opportunity! #Crypto $BTC $ETH $BAI #Blockchain #ETF #NFT

🧵1/7 💎 $wBAI – an AI bluechip 💎 Balance AI Network is a platform where AI is cooperative, transparent and secure. The goal is to create your personal AI trading assistant, watch the video and you will immediately understand what this will do! This #AI assistant isn't just a tool; it's your financial guide, providing insights on investments with precision. It's data-driven decision-making made personal! This is why big names in the #Crypto space are jumping on this opportunity! #Crypto $BTC $ETH $BAI #Blockchain #ETF #NFT

theCryptolusionist 🧙🏻

14,791 views • 2 years ago

Introducing SuperNinja – the world’s fastest deep research by NinjaTech AI powered by Cerebras: ‣ 1-2min for full answer instead of 10min ‣ 5x faster than o3, Gemini Pro etc. ‣ Same accuracy as measured by GAIA

Introducing SuperNinja – the world’s fastest deep research by NinjaTech AI powered by Cerebras: ‣ 1-2min for full answer instead of 10min ‣ 5x faster than o3, Gemini Pro etc. ‣ Same accuracy as measured by GAIA

Cerebras

25,541 views • 1 year ago

The Fastest AI Just Got Faster. Meet CS-4.

The Fastest AI Just Got Faster. Meet CS-4.

Cerebras

1,538,687 views • 1 month ago

Halo is now available on the App Store. It's a personal AI assistant that helps declutter the noise in your life and shows you what matters right now. I started building Halo last year with 3 goals in mind: - Surface what’s important before I have to ask - Understand my life through the apps I already use - Keep my personal data on my device Privacy is at the core of Halo and it's what sets it apart from other AI assistants. Excited to finally share it with you.

Halo is now available on the App Store. It's a personal AI assistant that helps declutter the noise in your life and shows you what matters right now. I started building Halo last year with 3 goals in mind: - Surface what’s important before I have to ask - Understand my life through the apps I already use - Keep my personal data on my device Privacy is at the core of Halo and it's what sets it apart from other AI assistants. Excited to finally share it with you.

Tanmay

44,673 views • 3 days ago

📁 Sam Altman says the real AI breakthrough will not be better reasoning, but total memory. An AI will be able to remember every conversation, email, and document across a person’s lifetime, identifying patterns and preferences humans never consciously express. Once memory becomes persistent, the idea of a personal assistant will fundamentally change.

📁 Sam Altman says the real AI breakthrough will not be better reasoning, but total memory. An AI will be able to remember every conversation, email, and document across a person’s lifetime, identifying patterns and preferences humans never consciously express. Once memory becomes persistent, the idea of a personal assistant will fundamentally change.

Jon Hernandez

4,272,261 views • 9 months ago