Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

1/🥇 For the first time ever... LLMs are running inside NVIDIA GPU TEEs — and accessible to everyone via OpenRouter 🧠 DeepSeek R1-70B & 🦙 LLaMA3.3 70B Instruct: Both models run inside secure enclaves on Phala’s TEE-powered infra.

PhalaNetwork's profile picture

Phala

143,073 subscribers

10,919 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

12 Kommentare

Profilbild von Phala Network
Phala Networkvor 1 Jahr

🚨 Major Milestone for AI Privacy 🚨 TEE-LLMs are first-ever live on @openrouterai — powered by Phala Network. We give you: 🔐 End-to-end privacy. ⚡️ Blazing speed. 📜 Verifiable LLM computation. Let's break it down.

Profilbild von Phala Network
Phala Networkvor 1 Jahr

2/ 🔍 What’s a TEE-LLM models? A Trusted Execution Environment is a secure hardware-based enclave. It ensures your prompts & model outputs are encrypted — even the operator can’t see them. More:

Profilbild von Phala Network
Phala Networkvor 1 Jahr

3/ Why does this matter? ✅ True privacy ✅ Remote attestation proves you're talking to the real TEE ✅ End-to-end encrypted model usage — even OpenRouter can’t snoop 🔗:

Profilbild von Phala Network
Phala Networkvor 1 Jahr

4/ 🖥️ OpenRouter + Phala = Seamless AI access You get the familiar OpenRouter experience, but backed by verifiable hardware privacy. A breakthrough: Web2-grade UX with Web3-grade security.

Profilbild von Phala Network
Phala Networkvor 1 Jahr

5/ 💰 Pricing: TEE-LLM models are not expensive! 🔹 LLaMA3.3-70B: $0.24 / 1m tokens 🔹 DeepSeek R1-70B: $0.46 / 1m tokens The costs of running your own AI models are also affordable & public:

Profilbild von Phala Network
Phala Networkvor 1 Jahr

6/ 🎮 This is just the beginning. The age of private, verifiable, decentralized AI is here. Phala’s infrastructure shows it’s possible — and live in production. 🔗 Explore:

Profilbild von Lab4crypto
Lab4cryptovor 1 Jahr

🚀 Don't gamble with your portfolio! Use our advanced hybrid quant risk tool using on/off-chain data and make informed decisions. 📈 Acess to 1000+ charts for your crypto journey. 📚Join our Premium Telegram for daily alerts. 📊+21 projects supported. 🏗️ Beginners and experts.

Profilbild von pinetwork
pinetworkvor 1 Jahr

@OpenRouterAI $pha at 10$

Profilbild von 4rifmln
4rifmlnvor 1 Jahr

@OpenRouterAI when Claude 3.7 sonnet sir ? 🗿

Profilbild von crAAzy BTC 🎭 🇦🇪
crAAzy BTC 🎭 🇦🇪vor 1 Jahr

@OpenRouterAI LLMs in secure enclaves on @PhalaNetwork? What an absolute game changer. This is a whole new era for AI privacy and computation. 💯🚀

Profilbild von Floyd 🥷
Floyd 🥷vor 1 Jahr

@OpenRouterAI Props to @PhalaNetwork and @openrouterai — combining TEEs with top-tier open models like DeepSeek and LLaMA3 is a serious unlock 🔥

Profilbild von godon
godonvor 1 Jahr

@OpenRouterAI Privacy is 4x the price? I guess it's good to put a number on privacy. However the avg. Person doesn't give 2 pennies

Ähnliche Videos

I bought the M4 Max 48GB RAM and first thing I did is to test local LLMs. It can barely run llama3.3 70b, but qwen2.5-coder 32b works very well. I'll test with MLX next ✌️
0:31

I bought the M4 Max 48GB RAM and first thing I did is to test local LLMs. It can barely run llama3.3 70b, but qwen2.5-coder 32b works very well. I'll test with MLX next ✌️

Daniel Nguyen

315,827 Aufrufe • vor 1 Jahr

Llama 3.3 70B 4-bit running on a 128GB M4 Max with MLX LM (~12 toks/sec) with mactop on the right. "Good enough", local, private and open models are now more accessible than ever!
0:29

Llama 3.3 70B 4-bit running on a 128GB M4 Max with MLX LM (~12 toks/sec) with mactop on the right. "Good enough", local, private and open models are now more accessible than ever!

Ivan Fioravanti ᯅ

43,929 Aufrufe • vor 1 Jahr

AkashChat provides access to 8 of the leading open-source AI models. Switch between models mid-conversation to leverage the strengths of each, while seamlessly maintaining the context. The chat below switches from Llama 3.3 70B to DeepSeek-R1.
1:14

AkashChat provides access to 8 of the leading open-source AI models. Switch between models mid-conversation to leverage the strengths of each, while seamlessly maintaining the context. The chat below switches from Llama 3.3 70B to DeepSeek-R1.

Akash Network

11,964 Aufrufe • vor 1 Jahr

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁
0:34

PSA: DeepSeek R1 Distill Llama 70B speculative decoding version is now live on Groq Inc for Dev Tier. We just made fast even faster for instant reasoning. 🏁

Hatice Ozen

44,675 Aufrufe • vor 1 Jahr

With all the DeepSeek drama, here is a quick 1min explanation of Private AI we are building at Nillion You can run AI models inside a secure enclave / TEE where all the information is transferred and processed privately without it being exposed. Coming soon.
1:00

With all the DeepSeek drama, here is a quick 1min explanation of Private AI we are building at Nillion You can run AI models inside a secure enclave / TEE where all the information is transferred and processed privately without it being exposed. Coming soon.

Tom 👓

30,187 Aufrufe • vor 1 Jahr

Running open source LLMs on Replit ⠕ feels like magic 🪄 Here's a demo of GPT4All 🦙 by Nomic running inside my Repl:
0:37

Running open source LLMs on Replit ⠕ feels like magic 🪄 Here's a demo of GPT4All 🦙 by Nomic running inside my Repl:

Zahid Khawaja

135,684 Aufrufe • vor 3 Jahren

HOLY FUNIONS! Groq makes DeepSeek R1 feel instant! Cooked up a chatbot using their Distill Llama 70B. Releasing the repo tomorrow. You control your data flow.
1:06

HOLY FUNIONS! Groq makes DeepSeek R1 feel instant! Cooked up a chatbot using their Distill Llama 70B. Releasing the repo tomorrow. You control your data flow.

Ray Fernando

54,028 Aufrufe • vor 1 Jahr

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!
1:34

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

Santiago

130,934 Aufrufe • vor 1 Jahr

Check out Hermes 4 70b & 405b models from Nous Research. Now available for you through both the Nous Research and Cline providers. (Nous Research brand booklet linked below)
0:21

Check out Hermes 4 70b & 405b models from Nous Research. Now available for you through both the Nous Research and Cline providers. (Nous Research brand booklet linked below)

Cline

31,903 Aufrufe • vor 7 Monaten

DeepSeek-R1-0528 is now live on Hyperbolic’s Serverless Inference! We also are the first to serve the latest DeepSeek model on Hugging Face. 🟣 Run it instantly:
0:20

DeepSeek-R1-0528 is now live on Hyperbolic’s Serverless Inference! We also are the first to serve the latest DeepSeek model on Hugging Face. 🟣 Run it instantly:

Hyperbolic

33,228 Aufrufe • vor 1 Jahr

Introducing → CodecFlow @CodecOpenFlow offers agent first infra powered by vision language models, making robotics and desktop operators simple Agents spin up compute, run models, and build autonomously with payments via x402 on @Solana 🔗
0:40

Introducing → CodecFlow @CodecOpenFlow offers agent first infra powered by vision language models, making robotics and desktop operators simple Agents spin up compute, run models, and build autonomously with payments via x402 on @Solana 🔗

Superteam UAE

33,841 Aufrufe • vor 3 Monaten

Running multi agents on open source models has always been a hit or miss until... Llama 3.1 on Groq Inc with 405b and 70b
0:41

Running multi agents on open source models has always been a hit or miss until... Llama 3.1 on Groq Inc with 405b and 70b

FlowiseAI

48,208 Aufrufe • vor 1 Jahr