Andrew Feldman
@andrewdfeldman
CEO and Founder @CerebrasSystems. I build teams that solve hard problems, grow heirloom tomatoes, dance tango and love Vizslas
We are just a little bit faster than@nvidia GPUs on Qwen 235B...18X faster. @CerebrasSystems inference is blazing fast...come build cool stuff on Cerebras inference
Code generation is one of the premier AI use cases. And @CerebrasSystems' Inference is the fastest API for coding applications. @cline makes coding easy, Cerebras + Cline make it blisteringly fast. There are lots of things worth waiting for, code generation isn't one of them.
Instant coffee?
The worst part of @CerebrasSystems inference? You don't time to make an espresso while Cline codes. Join our hackathon next Saturday to explore the new paradigm: instant inference. $5k in prizes → RSVP below
Shill away, my friend.
I was gonna stop shilling @CerebrasSystems but then they put @cline on their landing page get 1M of free credits below
I was gonna stop shilling @CerebrasSystems but then they put @cline on their landing page get 1M of free credits below
Now that is a serious problem.
The worst part of @CerebrasSystems inference? You don't time to make an espresso while Cline codes. Join our hackathon next Saturday to explore the new paradigm: instant inference. $5k in prizes → RSVP below
Congrats. Important work.
🇺🇸 Today is a day we have been working towards for six months. We are announcing America’s AI action plan putting us on the road to continued AI dominance. The three core themes: - Accelerate AI innovation - Build American AI infrastructure - Lead in international AI…
🇺🇸 Today is a day we have been working towards for six months. We are announcing America’s AI action plan putting us on the road to continued AI dominance. The three core themes: - Accelerate AI innovation - Build American AI infrastructure - Lead in international AI…
Say you wanted to code up a simple particle simulation for a web background...@CerebrasSystems and @cline make it dead simple, and blisteringly fast.... Cline makes coding easy. Cerebras makes it crazy fast.
Delivering blisteringly fast inference speeds to our partner @cline…check out the demo below.
> 2500 tokens per second > 40x faster than Sonnet-4 > 4 trillion transistor wafers (19x Nvidia B200) These are impressive numbers, but nothing beats a live demo. 1 million free tokens per day of lightning-fast qwen3-32b and qwen3-235b from @CerebrasSystems in Cline. Link below.
Am I the only one who is surprised that this doesn’t happen more often?
INEOS team car drove into a spectator on Peyresourde. 😬 #TDF2025
Third-party benchmark firm @ArtificialAnlys shows @CerebrasSystems is 20 X faster than @nvidia GPUs on Qwen 235B. Model intelligence on the Y axis. Speed on the X axis. The dots are different models running on NVIDIA GPUs, except the one that shows that Cerebras is 20x faster.
A simple straight forward way to access your favorite models. @CerebrasSystems, provides the fastest AI in the world, now available on @awscloud Marketplace…
The world's fastest AI inference is now available in @awscloud Marketplace. It's easier than ever to access models like @AIatMeta Llama, @Alibaba_Qwen, @deepseek_ai, consolidate billing, and experience the speed of Cerebras.
The world's fastest AI inference is now available in @awscloud Marketplace. It's easier than ever to access models like @AIatMeta Llama, @Alibaba_Qwen, @deepseek_ai, consolidate billing, and experience the speed of Cerebras.
What now constitutes an “action” shot … a good conversation.
@andrewdfeldman 👀