Cerebras
@CerebrasSystems
Followers
38K
Following
1K
Media
977
Statuses
2K
The world's fastest AI inference and training. Try the latest open models at: https://t.co/jREGhLI2nj
Sunnyvale, CA
Joined July 2016
OpenAI GPT-OSS-120B is live on Cerebras.3,000 tokens/s - fastest OpenAI model on record.1 second reasoning time.131K context.Go build something fantastic.
82
177
2K
3
1
28
Our intern @KevinTaylor00 made diet coke game mobile responsive with @cline and Qwen3-Coder on Cerebras, instantly ✨. try it now 👉
We built Death by Diet Coke in less than 30 seconds using Cerebras Code Pro, where you get higher rate limits and more power for Qwen3-Coder. We are opening the same number of Cerebras Code Pro/Max plans as diet coke cans in the office. First come, first serve.
3
5
32
We built Death by Diet Coke in less than 30 seconds using Cerebras Code Pro, where you get higher rate limits and more power for Qwen3-Coder. We are opening the same number of Cerebras Code Pro/Max plans as diet coke cans in the office. First come, first serve.
Cerebras Code: 20x faster than Claude, 1x the price. Today we are launching two monthly coding plans:. ➡️Cerebras Code Pro: $50/m – for indie developers.➡️Cerebras Code Max: $200/m – for power users with 5x rate limits. Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context,
5
8
73
GPT OSS 120B endpoints are not created equal. In AIME25 math evals, Artificial Analysis found Cerebras was #1 in accuracy.
22
13
338
Here’s what nobody tells you about MoE: the router can single-handedly destroy your model. You can have perfect expert network architecture, tuned hyperparameters, and unlimited compute, but if your router collapses, you’re back to dense model performance regardless of number of
5
13
105
Come build some really cool stuff with super fast inference ⚡️⚡️. rsvp 👉
partiful.com
Join Discord for details and info: https://discord.gg/32T8thKm It's been an exciting few weeks in AI, from GPT-5/gpt-oss to Opus 4.1 to Qwen/Kimi. Selected hackers will convene in SF this Sunday to...
Lots of new frontier models this week. So this Sunday, we’re hosting the Applied AI Hackathon in SF to push the limits of what’s possible. $100,000 in prizes. Judges including @karpathy and @swyx. 12 hours to build something that shouldn’t exist yet. Details & how to join👇
0
4
37
one shot vibe coding with gpt-oss-120b through anycoder by @huggingface. the future is here
5
17
138
RT @_akhaliq: vibe coding a Qwen3-4B-Instruct-2507 @Alibaba_Qwen chat app . Qwen3-Coder-480B-A35B-Instruct with @CerebrasSystems one shott….
0
9
0
You can use Cerebras' gpt-oss-120b to build realistic speech-to-speech voice interfaces with emotion via @hume_ai's new EVI 3. Perfect for your next voice ai project!. Link to try below 👇
7
29
255
GPT OSS 120B is a reasoning model.But we run it so fast it it feels like an instruct model
17
26
471
RT @reach_vb: The best open model currently available on Inference Providers, blazing fast! Powered by @CerebrasSystems 🔥. Try it out today….
0
12
0
Chat app is a little slow right now. We are seeing ~3700 TPS on OpenRouter .
3
3
79
RT @andrewdfeldman: In 2016, @sama and I first met. @OpenAI was a vision. @CerebrasSystems was powerpoint. Sam and the OpenAi founders be….
0
144
0
Live on OpenRouter.
Today, OpenAI returns to open source! 🚀. Excited to be a launch partner for gpt-oss, OpenAI’s new open-weight models with variable reasoning. First providers are @FireworksAI_HQ, @GroqInc, and @CerebrasSystems, with more to come! Here’s what's launching today 👇
3
2
94