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.

Multimodal reasoning has a latency problem. More video frames leads to more waiting. We built Damage Scout with Gemma 4 on Cerebras, running at over 2,300 toks/s, to show what fast multimodal inference unlocks. Damage Scout samples frames from a rental car walkaround, sends them to Gemma 4, gets... show more

Cerebras

62,708 subscribers

30,493 views • 13 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Cerebras

273,811 views • 24 days ago

We gave two agents the same task: “Find images matching this description.” Both use Gemma 4 31B. One runs on Cerebras. The other runs on GPUs. You can see the difference. Speed changes the product experience. What would you build if you didn't have to wait?

We gave two agents the same task: “Find images matching this description.” Both use Gemma 4 31B. One runs on Cerebras. The other runs on GPUs. You can see the difference. Speed changes the product experience. What would you build if you didn't have to wait?

Cerebras

141,957 views • 22 days ago

10 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds. We built a research agent with @Cerebras Inference and Unstructured that processes entire literature reviews so you become a subject expert faster

10 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds. We built a research agent with @Cerebras Inference and Unstructured that processes entire literature reviews so you become a subject expert faster

Cerebras

14,650 views • 4 months 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

128,577 views • 2 years ago

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.

Cerebras

383,060 views • 1 month ago

Multi-LoRA is in private preview on Cerebras Inference. Deploy one base model alongside a library of LoRA adapters. Switch between them per request, with no reloading, no separate deployments, and no latency cost. Available now for dedicated endpoint users. Reach out to your account rep to get access.

Multi-LoRA is in private preview on Cerebras Inference. Deploy one base model alongside a library of LoRA adapters. Switch between them per request, with no reloading, no separate deployments, and no latency cost. Available now for dedicated endpoint users. Reach out to your account rep to get access.

Cerebras

21,168 views • 1 month ago

Today, we’re launching Gemma 4, our most intelligent open models to date. Built with the same breakthrough technology as Gemini 3, Gemma 4 brings advanced reasoning to your personal hardware and devices. Here’s what Gemma 4 unlocks for developers: — Intelligence-per-parameter: Our 31B (Dense) and 26B (MoE) models deliver state-of-the-art performance for their size, outcompeting models 20x their size on Arena.ai — Commercial flexibility: Released under a permissive Apache 2.0 license for complete developer flexibility and digital sovereignty — Agentic workflows: Native support for function-calling and structured JSON output allows you to build reliable, autonomous agents — Multimodal edge AI: The E2B and E4B models bring native vision, audio, and low latency to mobile and IoT devices — Long-context reasoning: Up to 256K context windows allow you to process entire repositories or large documents in a single prompt Whether you're building global applications in 140+ languages or local-first AI code assistants, Gemma 4 is built to be your foundation. Explore in Google AI Studio or download the weights on Hugging Face, Kaggle, and ollama.

Today, we’re launching Gemma 4, our most intelligent open models to date. Built with the same breakthrough technology as Gemini 3, Gemma 4 brings advanced reasoning to your personal hardware and devices. Here’s what Gemma 4 unlocks for developers: — Intelligence-per-parameter: Our 31B (Dense) and 26B (MoE) models deliver state-of-the-art performance for their size, outcompeting models 20x their size on Arena.ai — Commercial flexibility: Released under a permissive Apache 2.0 license for complete developer flexibility and digital sovereignty — Agentic workflows: Native support for function-calling and structured JSON output allows you to build reliable, autonomous agents — Multimodal edge AI: The E2B and E4B models bring native vision, audio, and low latency to mobile and IoT devices — Long-context reasoning: Up to 256K context windows allow you to process entire repositories or large documents in a single prompt Whether you're building global applications in 140+ languages or local-first AI code assistants, Gemma 4 is built to be your foundation. Explore in Google AI Studio or download the weights on Hugging Face, Kaggle, and ollama.

Google AI

1,669,468 views • 3 months ago

Our coding workflows were designed to accommodate slow inference. OpenAI's Codex Spark powered by Cerebras changes the game. Here's how we make the most out of 1,200 tokens per second, with Sarah Fong.

Our coding workflows were designed to accommodate slow inference. OpenAI's Codex Spark powered by Cerebras changes the game. Here's how we make the most out of 1,200 tokens per second, with Sarah Fong.

Cerebras

13,370 views • 4 months ago

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

Cerebras

299,029 views • 9 months ago

gpt-oss-120b is one of the most-used models on Cerebras Inference. We sat down with Anastasios Nikolas Angelopoulos from Arena.ai and @SarahChieng to break down its strengths, weaknesses, and where it's outperforming. Here's what he's seeing.

gpt-oss-120b is one of the most-used models on Cerebras Inference. We sat down with Anastasios Nikolas Angelopoulos from Arena.ai and @SarahChieng to break down its strengths, weaknesses, and where it's outperforming. Here's what he's seeing.

Cerebras

13,076 views • 4 months 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

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.

Cerebras

93,023 views • 3 months ago

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.

Cerebras

287,606 views • 5 months ago

🎁 We're giving away 5 Windsurf plans ($250 credit each)! Try SWE-1.6 — Cognition’s latest fast and intelligent agentic coding model, powered by Cerebras. In a side-by-side with Claude, the speed difference is clear. More iterations, faster fixes, better code. 💬Comment why you want access to enter. Five winners will be selected at random within 48 hours.

🎁 We're giving away 5 Windsurf plans ($250 credit each)! Try SWE-1.6 — Cognition’s latest fast and intelligent agentic coding model, powered by Cerebras. In a side-by-side with Claude, the speed difference is clear. More iterations, faster fixes, better code. 💬Comment why you want access to enter. Five winners will be selected at random within 48 hours.

Cerebras

105,033 views • 2 months 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

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama *3B* - It's like the perf of a new hardware generation in a single software release Available now at

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama 3B - It's like the perf of a new hardware generation in a single software release Available now at

Cerebras

236,090 views • 1 year 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 • 11 months ago

🟧 Cerebras Inference self-serve is finally here 🟧 – Pay by credit card starting at $10 – Run Qwen3 Coder, GPT OSS & more at 2,000+ TPS – 20x the speed of GPU-based model providers Go ahead. Melt our wafers.

🟧 Cerebras Inference self-serve is finally here 🟧 – Pay by credit card starting at $10 – Run Qwen3 Coder, GPT OSS & more at 2,000+ TPS – 20x the speed of GPU-based model providers Go ahead. Melt our wafers.

Cerebras

52,763 views • 9 months ago

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:

Cerebras

706,789 views • 1 year ago

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,319 views • 1 month ago