Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Perplexity Pro is Now Powered by Cerebras. Perplexity Sonar, now running on Cerebras Inference, delivers answers at an unprecedented 1,200 tokens/s – 10x faster than comparable models​.

cerebras's profile picture

Cerebras

56,648 subscribers

68,007 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieNachrichten & PolitikBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

No more waitlist – Cerebras inference API is open to all! 1M free tokens/day 20x GPU speed Reasoning in ~1 second It's time to build!
0:18

No more waitlist – Cerebras inference API is open to all! 1M free tokens/day 20x GPU speed Reasoning in ~1 second It's time to build!

Cerebras

108,466 Aufrufe • vor 1 Jahr

Cerebras and CrowdStrike are partnering to power Falcon AIDR on the world’s fastest inference. AI attacks move in seconds, and cybersecurity can’t wait in a queue. Together, CrowdStrike and Cerebras are enabling security AI to detect, reason, and respond at machine speed.
0:15

Cerebras and CrowdStrike are partnering to power Falcon AIDR on the world’s fastest inference. AI attacks move in seconds, and cybersecurity can’t wait in a queue. Together, CrowdStrike and Cerebras are enabling security AI to detect, reason, and respond at machine speed.

Cerebras

407,530 Aufrufe • vor 20 Tagen

Cerebras Code Plans are open for business and massively upgraded. Pro Plans ($50): 165k▶️300k TPM @ 24M Tokens/day Max Plans ($200): 300k▶️400k TPM @ 120M Tokens/day More vibing, more tokens. Keep sending us feedback!
0:16

Cerebras Code Plans are open for business and massively upgraded. Pro Plans ($50): 165k▶️300k TPM @ 24M Tokens/day Max Plans ($200): 300k▶️400k TPM @ 120M Tokens/day More vibing, more tokens. Keep sending us feedback!

Cerebras

51,711 Aufrufe • vor 11 Monaten

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.
0:10

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

47,752 Aufrufe • vor 1 Jahr

🟪 Qwen3-235B 2507 Instruct is live on Cerebras 1400 TPS • 131K Context • 230ms TTFT $0.6 | $1.2 per M tokens Try chat: Get API key: Pay-as-you-go via
0:10

🟪 Qwen3-235B 2507 Instruct is live on Cerebras 1400 TPS • 131K Context • 230ms TTFT $0.6 | $1.2 per M tokens Try chat: Get API key: Pay-as-you-go via

Cerebras

536,432 Aufrufe • vor 1 Jahr

Trading on Avantis is now faster than ever, powered by Pyth Network 🔮 pro feeds ⚡
0:13

Trading on Avantis is now faster than ever, powered by Pyth Network 🔮 pro feeds ⚡

Avantis

18,040 Aufrufe • vor 6 Monaten

You can now access Box and Dropbox, in addition to Google Drive, OneDrive, and SharePoint with Perplexity Enterprise Pro. Get comprehensive answers by running Deep Research on internal files and the web, all with enterprise-grade security.
0:11

You can now access Box and Dropbox, in addition to Google Drive, OneDrive, and SharePoint with Perplexity Enterprise Pro. Get comprehensive answers by running Deep Research on internal files and the web, all with enterprise-grade security.

Perplexity

142,946 Aufrufe • vor 1 Jahr

Perplexity users can now onramp crypto powered by the MoonPay Model Context Protocol (MCP) get started in seconds on Perplexity using our new Custom Connector to give your agents access to crypto here's a look at how it works:
0:19

Perplexity users can now onramp crypto powered by the MoonPay Model Context Protocol (MCP) get started in seconds on Perplexity using our new Custom Connector to give your agents access to crypto here's a look at how it works:

MoonPay 🟣

56,550 Aufrufe • vor 1 Monat

Perplexity Computer is now available for Pro subscribers. Access Computer’s full suite of 20+ advanced models, prebuilt and custom skills, and hundreds of connectors. Max subscribers receive monthly credits and higher spend limits than Pro.
0:12

Perplexity Computer is now available for Pro subscribers. Access Computer’s full suite of 20+ advanced models, prebuilt and custom skills, and hundreds of connectors. Max subscribers receive monthly credits and higher spend limits than Pro.

Perplexity

485,263 Aufrufe • vor 5 Monaten

Inference on UOMI is now free. Start building with frontier open-source models at no cost: • MiniMax M2.7 • Qwen 3.6 27B • Qwen 3.6 35B A3B • Google Gemma 4 26B A4B • Google Gemma 4 31B Powered by the UOMI Inference Network. Start inferencing:
0:14

Inference on UOMI is now free. Start building with frontier open-source models at no cost: • MiniMax M2.7 • Qwen 3.6 27B • Qwen 3.6 35B A3B • Google Gemma 4 26B A4B • Google Gemma 4 31B Powered by the UOMI Inference Network. Start inferencing:

Uomi

12,566 Aufrufe • vor 2 Monaten

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI
0:15

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI

Adrien Grondin

160,808 Aufrufe • vor 4 Monaten

Tick pricing is now live on Avantis, powered by Pyth Network 🔮’s pro feeds. Cross-asset traders can now scalp every tick (every price update). Trade global markets at the speed of the market, with self-custody and fully onchain execution. (Way) better than CEXs.
0:15

Tick pricing is now live on Avantis, powered by Pyth Network 🔮’s pro feeds. Cross-asset traders can now scalp every tick (every price update). Trade global markets at the speed of the market, with self-custody and fully onchain execution. (Way) better than CEXs.

Avantis

13,273 Aufrufe • vor 5 Monaten

Grok 2 mini is now 2x faster than it was yesterday. In the last three days Lianmin Zheng and Saeed Maleki rewrote our inference stack from scratch using SGLang ( This has also allowed us to serve the big Grok 2 model, which requires multi-host inference, at a reasonable speed. Both models didn’t just get faster, but also slightly more accurate. Stay tuned for further speed improvements!
0:11

Grok 2 mini is now 2x faster than it was yesterday. In the last three days Lianmin Zheng and Saeed Maleki rewrote our inference stack from scratch using SGLang ( This has also allowed us to serve the big Grok 2 model, which requires multi-host inference, at a reasonable speed. Both models didn’t just get faster, but also slightly more accurate. Stay tuned for further speed improvements!

Igor Babuschkin

1,803,113 Aufrufe • vor 1 Jahr

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇
0:13

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇

Xenova

12,557 Aufrufe • vor 1 Jahr

ABot World 0.5B is out! we have now world models at home, running in real-time on consumer GPU feed it an initial image, steer it with with your keyboard 🌎 you can run it locally or play now on spaces ▶️
0:18

ABot World 0.5B is out! we have now world models at home, running in real-time on consumer GPU feed it an initial image, steer it with with your keyboard 🌎 you can run it locally or play now on spaces ▶️

Hugging Apps

140,096 Aufrufe • vor 13 Tagen

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!
0:12

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!

Perplexity

274,587 Aufrufe • vor 3 Jahren

Deploy and run LLMs directly on your phone! Unsloth now lets you fine-tune LLMs and deploy them 100% locally on iOS/Android devices. The video shows this in action, where I ran Qwen3 on an iPhone 17 Pro at ~25 tokens/s. I have shared a guide in the replies.
0:14

Deploy and run LLMs directly on your phone! Unsloth now lets you fine-tune LLMs and deploy them 100% locally on iOS/Android devices. The video shows this in action, where I ran Qwen3 on an iPhone 17 Pro at ~25 tokens/s. I have shared a guide in the replies.

Avi Chawla

24,530 Aufrufe • vor 7 Monaten

PRO GAMER FACE OFF 2026 – GROK 5 RIGGED WITH 10X THE POWER OF GROK 4 xAI is calling out pro gamers. Grok 5, in the other corner, grins with 10x more confidence! Game Truth: •⁠ ⁠Grok 5 learns any game by reading, not grinding •⁠ ⁠Plays with human eyes and human reaction speed •⁠ ⁠Built on 6T parameters backed by 10x Grok 4’s compute •⁠ ⁠Drop date lines up with early 2026 – pros should hydrate now When the match starts, the only question is who blinks first - and it won’t be Grok 5! Source: Elon Musk
0:19

PRO GAMER FACE OFF 2026 – GROK 5 RIGGED WITH 10X THE POWER OF GROK 4 xAI is calling out pro gamers. Grok 5, in the other corner, grins with 10x more confidence! Game Truth: •⁠ ⁠Grok 5 learns any game by reading, not grinding •⁠ ⁠Plays with human eyes and human reaction speed •⁠ ⁠Built on 6T parameters backed by 10x Grok 4’s compute •⁠ ⁠Drop date lines up with early 2026 – pros should hydrate now When the match starts, the only question is who blinks first - and it won’t be Grok 5! Source: Elon Musk

Mario Nawfal

25,085 Aufrufe • vor 8 Monaten

I just ran Gemma 4 31B on @CerebrasSystems at 1,800+ tokens/sec and it's multimodal. For context: that's 35x faster than a typical GPU endpoint, and the first token (reasoning included) lands in 1.5 seconds. This isn't a benchmark slide, I recorded the inference live. Prompt I used: "Create a simulation of an iPhone. Include at least one working dummy note taking app, a functional notification pulldown, high quality graphics, single HTML file, any libs via CDN." - Generation time: 3 seconds. - Notes app worked. - Notification panel worked. - Rendered first try. This is what wafer-scale inference unlocks, not just "faster," but a different category of product. When generation is this fast, you stop waiting and start iterating in real time. Why this matters: Gemma 4 31B is Google DeepMind's flagship open weight model, Apache 2.0 licensed, dense (not MoE), and built for efficiency over raw parameter count. It scores close to Claude Haiku 4.5 on the Artificial Analysis Intelligence Index (30 vs 29) but runs ~18x faster on Cerebras. It's also the first multimodal model on Cerebras's platform, meaning you can now feed it screenshots, documents, charts, and UI states at wafer scale speed. # Applications I'm most excited about: - Screenshot → Insight: Drop in a dashboard or document screenshot, get structured findings back instantly. no waiting, no batching. - Live UI generation: Full interactive interfaces (like my iPhone sim) generated and rendered in under 2 seconds. - Screenshot -> Patch: Feed it a broken UI + console error, get a minimal code fix and verification steps back. - Computer use & agentic loops: See -> reason -> act - verify, fast enough to keep a human in the loop instead of waiting on the model. - Long context summarization: Full research reports condensed into decision ready summaries you can read and requery in one sitting. The bigger unlock isn't the speed number itself, it's that agentic and multimodal loops (see -> reason -> output -> tool call -> verify -> retry) finally run in real time instead of feeling sluggish. As Logan Kilpatrick (Logan Kilpatrick) put it: "If every model was doing 2,000 tokens per second, you wouldn't build the same product and just have it be faster, you'd build different products." Gemma 4 31B is live now on Cerebras Inference Cloud in public preview. If you're building multimodal, agentic, or real time apps, this is worth testing today. What would you build with such insane inference throughput?
0:12

I just ran Gemma 4 31B on @CerebrasSystems at 1,800+ tokens/sec and it's multimodal. For context: that's 35x faster than a typical GPU endpoint, and the first token (reasoning included) lands in 1.5 seconds. This isn't a benchmark slide, I recorded the inference live. Prompt I used: "Create a simulation of an iPhone. Include at least one working dummy note taking app, a functional notification pulldown, high quality graphics, single HTML file, any libs via CDN." - Generation time: 3 seconds. - Notes app worked. - Notification panel worked. - Rendered first try. This is what wafer-scale inference unlocks, not just "faster," but a different category of product. When generation is this fast, you stop waiting and start iterating in real time. Why this matters: Gemma 4 31B is Google DeepMind's flagship open weight model, Apache 2.0 licensed, dense (not MoE), and built for efficiency over raw parameter count. It scores close to Claude Haiku 4.5 on the Artificial Analysis Intelligence Index (30 vs 29) but runs ~18x faster on Cerebras. It's also the first multimodal model on Cerebras's platform, meaning you can now feed it screenshots, documents, charts, and UI states at wafer scale speed. # Applications I'm most excited about: - Screenshot → Insight: Drop in a dashboard or document screenshot, get structured findings back instantly. no waiting, no batching. - Live UI generation: Full interactive interfaces (like my iPhone sim) generated and rendered in under 2 seconds. - Screenshot -> Patch: Feed it a broken UI + console error, get a minimal code fix and verification steps back. - Computer use & agentic loops: See -> reason -> act - verify, fast enough to keep a human in the loop instead of waiting on the model. - Long context summarization: Full research reports condensed into decision ready summaries you can read and requery in one sitting. The bigger unlock isn't the speed number itself, it's that agentic and multimodal loops (see -> reason -> output -> tool call -> verify -> retry) finally run in real time instead of feeling sluggish. As Logan Kilpatrick (Logan Kilpatrick) put it: "If every model was doing 2,000 tokens per second, you wouldn't build the same product and just have it be faster, you'd build different products." Gemma 4 31B is live now on Cerebras Inference Cloud in public preview. If you're building multimodal, agentic, or real time apps, this is worth testing today. What would you build with such insane inference throughput?

Alok

12,962 Aufrufe • vor 1 Monat