Loading video...

Video Failed to Load

Go Home

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's profile picture

Cerebras

56,147 subscribers

21,168 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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.
1:16

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

"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.
0:37

"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

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:
2:08

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

269,017 views • 20 days 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:
0:21

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

706,706 views • 1 year ago

Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. →
0:42

Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. →

LiveKit

159,093 views • 4 months 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.
1:06

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

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.
5:26

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

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.
2:46

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

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 back structured findings and box coordinates, then renders an annotated damage report in under 6 seconds. Same task. Same frames. A complete different experience powered by Cerebras ⚡️
0:56

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 back structured findings and box coordinates, then renders an annotated damage report in under 6 seconds. Same task. Same frames. A complete different experience powered by Cerebras ⚡️

Cerebras

30,493 views • 9 days ago

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, and no weekly limits. Sign up now:
0:43

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, and no weekly limits. Sign up now:

Cerebras

461,227 views • 11 months ago

Doc-to-LoRA: What if you could online distill documents into your LLM weights without training? 🚀 Stoked to share our new work on instant LLM adaptation using meta-learned hypernetworks 📷📝 Building on our previous Text-to-LoRA work, we doc-condition a hypernetwork to output LoRA adapters, improving the base LLM's effective context window. The hypernetwork is meta-trained on 1000s of summarization tasks and shows remarkable compression capabilities at low latency 📈 🧑‍🔬 Work led by Rujikorn (Tan) Charakorn with Edoardo Cetin & Shin Useka at Sakana AI 📷
0:56

Doc-to-LoRA: What if you could online distill documents into your LLM weights without training? 🚀 Stoked to share our new work on instant LLM adaptation using meta-learned hypernetworks 📷📝 Building on our previous Text-to-LoRA work, we doc-condition a hypernetwork to output LoRA adapters, improving the base LLM's effective context window. The hypernetwork is meta-trained on 1000s of summarization tasks and shows remarkable compression capabilities at low latency 📈 🧑‍🔬 Work led by Rujikorn (Tan) Charakorn with Edoardo Cetin & Shin Useka at Sakana AI 📷

Robert Lange

37,387 views • 4 months ago

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.
0:45

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

48,760 views • 4 months ago

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
0:33

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 views • 3 months ago

GLM 4.7 is one of the top open-source models on LM Arena—and it's going toe-to-toe with Claude Opus 4.5 and Gemini Pro. We sat down with Anastasios Nikolas Angelopoulos, co-founder and CEO of Arena.ai, to break down 8,000+ developer votes: → Within 30 points of Gemini Pro in math & coding → Frontier-level multi-turn & instruction following → The open-source model devs are actually switching to The best part? You can run it at 1,500+ tokens/sec on Cerebras—for free.
4:14

GLM 4.7 is one of the top open-source models on LM Arena—and it's going toe-to-toe with Claude Opus 4.5 and Gemini Pro. We sat down with Anastasios Nikolas Angelopoulos, co-founder and CEO of Arena.ai, to break down 8,000+ developer votes: → Within 30 points of Gemini Pro in math & coding → Frontier-level multi-turn & instruction following → The open-source model devs are actually switching to The best part? You can run it at 1,500+ tokens/sec on Cerebras—for free.

Cerebras

28,515 views • 5 months ago

GLM-4.7 from Z.ai is live on Cerebras! - Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning - Record coding speed: ~1,000 tokens per second (up to 1,700 TPS for other uses) - Strong price-performance: ~10x higher than Sonnet 4.5
0:39

GLM-4.7 from Z.ai is live on Cerebras! - Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning - Record coding speed: ~1,000 tokens per second (up to 1,700 TPS for other uses) - Strong price-performance: ~10x higher than Sonnet 4.5

Cerebras

134,887 views • 6 months ago

API-based voice interaction works great, but scaling it to millions of free users is another story. Gradium Phonon: natural voices, multilingual, voice cloning, running locally on a smartphone CPU. No server, no latency, no per-call cost. Game devs, app builders: private beta is open, apply below ⬇️
0:27

API-based voice interaction works great, but scaling it to millions of free users is another story. Gradium Phonon: natural voices, multilingual, voice cloning, running locally on a smartphone CPU. No server, no latency, no per-call cost. Game devs, app builders: private beta is open, apply below ⬇️

Gradium

47,519 views • 3 months 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
0:26

🚨 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

236,067 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
1:17

📣 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

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.
0:46

Character LoRA on Flux – sneak peak 👀 I trained a model on 15 character images (same pose, different expressions) and now I can generate endless variants in new setups and poses. One image per inference, perfect consistency (both style + subject) with over 90% usable straight out of the box. Video below 👇 Trained on Scenario today.

Emm | scenario.com

48,818 views • 1 year ago

Been testing x402 with Veil.Cash x402 endpoint, signing via EIP-3009, send USDC with no onchain link across Base - fluidkey.eth to get a fresh PayTo address each time - x402 filled via Coinbase 🛡️ facilitator - USDC sent out from Veil relayer Result: no link between in/out txs. Agents just hit one endpoint + sign. Still early, but promising.
0:26

Been testing x402 with Veil.Cash x402 endpoint, signing via EIP-3009, send USDC with no onchain link across Base - fluidkey.eth to get a fresh PayTo address each time - x402 filled via Coinbase 🛡️ facilitator - USDC sent out from Veil relayer Result: no link between in/out txs. Agents just hit one endpoint + sign. Still early, but promising.

Apex777.eth

10,597 views • 3 months ago