Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 1 год назад •via X (Twitter)

Наука и технологииНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 12

Фото профиля Phala Network
Phala Network1 год назад

🚨 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.

Фото профиля Phala Network
Phala Network1 год назад

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:

Фото профиля Phala Network
Phala Network1 год назад

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 🔗:

Фото профиля Phala Network
Phala Network1 год назад

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.

Фото профиля Phala Network
Phala Network1 год назад

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:

Фото профиля Phala Network
Phala Network1 год назад

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:

Фото профиля Lab4crypto
Lab4crypto1 год назад

🚀 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.

Фото профиля pinetwork
pinetwork1 год назад

@OpenRouterAI $pha at 10$

Фото профиля 4rifmln
4rifmln1 год назад

@OpenRouterAI when Claude 3.7 sonnet sir ? 🗿

Фото профиля crAAzy BTC 🎭 🇦🇪
crAAzy BTC 🎭 🇦🇪1 год назад

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

Фото профиля Floyd 🥷
Floyd 🥷1 год назад

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

Фото профиля godon
godon1 год назад

@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

Похожие видео

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 просмотров • 1 год назад

The World’s First Truly Decentralized ChatGPT right at your fingertips: Community-hosted DeepSeek Running on Blockchain-powered AI Terminal! (1/n) Today, ChainOpera AI is proud to make history: we’ve launched the world’s first end-to-end five-layer decentralized AI stack — live in an iOS app ( giving users free access to models like DeepSeek-R1 and diverse community-built Agents. From prompt to response, human language tokens and crypto tokens flow through five layers: App, Agent, Model, GPU, and AI Chain + Smart Contracts. ChainOpera brings true decentralization to every layer — opening the AI ecosystem to users, model builders, agent devs, GPU providers, and data contributors to participate and earn.
1:03

The World’s First Truly Decentralized ChatGPT right at your fingertips: Community-hosted DeepSeek Running on Blockchain-powered AI Terminal! (1/n) Today, ChainOpera AI is proud to make history: we’ve launched the world’s first end-to-end five-layer decentralized AI stack — live in an iOS app ( giving users free access to models like DeepSeek-R1 and diverse community-built Agents. From prompt to response, human language tokens and crypto tokens flow through five layers: App, Agent, Model, GPU, and AI Chain + Smart Contracts. ChainOpera brings true decentralization to every layer — opening the AI ecosystem to users, model builders, agent devs, GPU providers, and data contributors to participate and earn.

ChainOpera AI

589,917 просмотров • 1 год назад

offers full-stack privacy across queries, data, payments and devices / hardware 1. The best open-source models (eg. Kimi K2.5) served in secure enclaves (TEEs) 2. The best closed-source models (eg. GPT-5.2 Pro) with queries pooled into proxy servers and PII anonymized with a specialized Silo model 3. The only available implementation of private Deep Research for secure reasoning 4. Fully private crypto payments via Zcash or discounted payments with FAI 5. A hardware offering to run everything on-prem from your own home with 288 GB GPU RAM (Silo Box) All with encrypted sync between devices so users can uniformly + privately access their AI sessions
0:35

offers full-stack privacy across queries, data, payments and devices / hardware 1. The best open-source models (eg. Kimi K2.5) served in secure enclaves (TEEs) 2. The best closed-source models (eg. GPT-5.2 Pro) with queries pooled into proxy servers and PII anonymized with a specialized Silo model 3. The only available implementation of private Deep Research for secure reasoning 4. Fully private crypto payments via Zcash or discounted payments with FAI 5. A hardware offering to run everything on-prem from your own home with 288 GB GPU RAM (Silo Box) All with encrypted sync between devices so users can uniformly + privately access their AI sessions

Freysa

16,647 просмотров • 4 месяцев назад

Leo Nightly now runs GLM-5 inside NEAR AI's Trusted Execution Environments, upgrading from DeepSeek V3.1. GLM-5 is currently one of the best open weight models from that leads every other open model on reasoning, coding, and agentic benchmarks. It's running inside Nvidia-backed TEEs via NEAR AI, which means your conversations are processed in a hardware-secured enclave where no one, not Brave, not NEAR, not anyone, can see your prompts or responses. Every computation is cryptographically signed so you can verify the model running is actually the model you selected. This is what we mean by moving from "trust me bro" to "trust but verify." Most AI assistants ask you to take their privacy claims on faith. Leo with NEAR AI TEEs gives you cryptographic proof. Update to the latest Nightly build and select GLM-5 with the "Verifiably Private with NEAR AI TEE" label in Leo to try it.
0:51

Leo Nightly now runs GLM-5 inside NEAR AI's Trusted Execution Environments, upgrading from DeepSeek V3.1. GLM-5 is currently one of the best open weight models from that leads every other open model on reasoning, coding, and agentic benchmarks. It's running inside Nvidia-backed TEEs via NEAR AI, which means your conversations are processed in a hardware-secured enclave where no one, not Brave, not NEAR, not anyone, can see your prompts or responses. Every computation is cryptographically signed so you can verify the model running is actually the model you selected. This is what we mean by moving from "trust me bro" to "trust but verify." Most AI assistants ask you to take their privacy claims on faith. Leo with NEAR AI TEEs gives you cryptographic proof. Update to the latest Nightly build and select GLM-5 with the "Verifiably Private with NEAR AI TEE" label in Leo to try it.

Brave Nightly

52,362 просмотров • 4 месяцев назад

The free UE5.5 AI motion capture plugin is compatible with Unity, Blender, and VMC. It supports both real-time motion capture via webcam and video uploads to generate 3D motion data. Powered by a 1-billion-parameter motion model running locally on your computer, it requires 8GB of VRAM for real-time processing. Compatible with Nvidia, AMD, and Intel GPUs, it can leverage NVIDIA CUDA to significantly boost graphics computation efficiency.
1:25

The free UE5.5 AI motion capture plugin is compatible with Unity, Blender, and VMC. It supports both real-time motion capture via webcam and video uploads to generate 3D motion data. Powered by a 1-billion-parameter motion model running locally on your computer, it requires 8GB of VRAM for real-time processing. Compatible with Nvidia, AMD, and Intel GPUs, it can leverage NVIDIA CUDA to significantly boost graphics computation efficiency.

CYANPUPPETS

17,842 просмотров • 1 год назад

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.
0:23

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

ollama

219,398 просмотров • 2 лет назад

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.
2:24

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.

Grummz

30,573 просмотров • 1 месяц назад

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below
0:59

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

starmex

977,841 просмотров • 1 месяц назад

I'm running Llama 4 Maverick at 620 t/s! I'm living in the future! Honestly, a large language model running this fast is something straight out of a sci-fi movie. Speeds like this will enable a whole new world of applications that aren't possible today. For reference, GPT-4o, which is probably the most popular OpenAI model, runs between 60 and 110 t/s. The secret here: I'm not running AI at Meta's Llama 4 Maverick on a GPU. I'm using the SambaNova Cloud (my sponsor) and their custom SN40L chips. They are optimized from the ground up for running AI workflows. Right now, SambaNova Cloud runs DeepSeek, Qwen, Whisper, and the entire family of Llama models on these chips. You can check the speed of each of these models using SambaNova Cloud's Playground (see the attached video). It's completely free, and that's how I'm measuring their speeds. For example, I also tried DeepSeek R1 (the latest version from May) and, oh boy! DeepSeek R1 is a huge 671B parameter model. It's probably the best open reasoning model in the world, and it runs at 140 tokens per second! !!! Inference time on an SN40L is night and day from what you'll get from a GPU. Here is why this is big: If you are running an agentic workflow that uses multiple models simultaneously on a GPU, it will need to swap models in and out of memory (because not every model fits). A single SNL40 chip can simultaneously hold over 100 models (trillions of parameters) in memory. If you are using open models, try the SambaCloud API to see what lightning speed looks like. Here is how: 1. Create a free account at: 2. Check the QuickStart guide: If you try the playground, check the speed you're getting with Llama 4 and DeepSeek, and post the results below. I've seen much higher numbers than I posted here, so I'm curious to see whether geography affects the speed.
1:10

I'm running Llama 4 Maverick at 620 t/s! I'm living in the future! Honestly, a large language model running this fast is something straight out of a sci-fi movie. Speeds like this will enable a whole new world of applications that aren't possible today. For reference, GPT-4o, which is probably the most popular OpenAI model, runs between 60 and 110 t/s. The secret here: I'm not running AI at Meta's Llama 4 Maverick on a GPU. I'm using the SambaNova Cloud (my sponsor) and their custom SN40L chips. They are optimized from the ground up for running AI workflows. Right now, SambaNova Cloud runs DeepSeek, Qwen, Whisper, and the entire family of Llama models on these chips. You can check the speed of each of these models using SambaNova Cloud's Playground (see the attached video). It's completely free, and that's how I'm measuring their speeds. For example, I also tried DeepSeek R1 (the latest version from May) and, oh boy! DeepSeek R1 is a huge 671B parameter model. It's probably the best open reasoning model in the world, and it runs at 140 tokens per second! !!! Inference time on an SN40L is night and day from what you'll get from a GPU. Here is why this is big: If you are running an agentic workflow that uses multiple models simultaneously on a GPU, it will need to swap models in and out of memory (because not every model fits). A single SNL40 chip can simultaneously hold over 100 models (trillions of parameters) in memory. If you are using open models, try the SambaCloud API to see what lightning speed looks like. Here is how: 1. Create a free account at: 2. Check the QuickStart guide: If you try the playground, check the speed you're getting with Llama 4 and DeepSeek, and post the results below. I've seen much higher numbers than I posted here, so I'm curious to see whether geography affects the speed.

Santiago

34,148 просмотров • 1 год назад

Here's my 5-hour conversation with Dylan Patel and Nathan Lambert on DeepSeek, China, OpenAI, NVIDIA, xAI, Google, Anthropic, Meta, Microsoft, TSMC, Stargate, megacluster buildouts, RL, reasoning, and a lot of other topics at the cutting edge of AI. This is was a mind-blowing, super-technical, and fun conversation. Yes, we discuss r1 and o3-mini, but more importantly we look into the future of technology, geopolitics, and humanity in a world that stands on the precipice of a global AI revolution. The first 4 hours are here on X (4 hours is current limit), and the full 5 hours are up everywhere else. Links in comment. Timestamps: 0:00 - Introduction 3:33 - DeepSeek-R1 and DeepSeek-V3 25:07 - Low cost of training 51:25 - DeepSeek compute cluster 58:57 - Export controls on GPUs to China 1:09:16 - AGI timeline 1:18:41 - China's manufacturing capacity 1:26:36 - Cold war with China 1:31:05 - TSMC and Taiwan 1:54:44 - Best GPUs for AI 2:09:36 - Why DeepSeek is so cheap 2:22:55 - Espionage 2:31:57 - Censorship 2:44:52 - Andrej Karpathy and magic of RL 2:55:23 - OpenAI o3-mini vs DeepSeek r1 3:14:31 - NVIDIA 3:18:58 - GPU smuggling 3:25:36 - DeepSeek training on OpenAI data 3:36:04 - AI megaclusters 4:11:26 - Who wins the race to AGI? 4:21:39 - AI agents 4:30:21 - Programming and AI 4:37:49 - Open source 4:47:01 - Stargate 4:54:30 - Future of AI
3:59:56

Here's my 5-hour conversation with Dylan Patel and Nathan Lambert on DeepSeek, China, OpenAI, NVIDIA, xAI, Google, Anthropic, Meta, Microsoft, TSMC, Stargate, megacluster buildouts, RL, reasoning, and a lot of other topics at the cutting edge of AI. This is was a mind-blowing, super-technical, and fun conversation. Yes, we discuss r1 and o3-mini, but more importantly we look into the future of technology, geopolitics, and humanity in a world that stands on the precipice of a global AI revolution. The first 4 hours are here on X (4 hours is current limit), and the full 5 hours are up everywhere else. Links in comment. Timestamps: 0:00 - Introduction 3:33 - DeepSeek-R1 and DeepSeek-V3 25:07 - Low cost of training 51:25 - DeepSeek compute cluster 58:57 - Export controls on GPUs to China 1:09:16 - AGI timeline 1:18:41 - China's manufacturing capacity 1:26:36 - Cold war with China 1:31:05 - TSMC and Taiwan 1:54:44 - Best GPUs for AI 2:09:36 - Why DeepSeek is so cheap 2:22:55 - Espionage 2:31:57 - Censorship 2:44:52 - Andrej Karpathy and magic of RL 2:55:23 - OpenAI o3-mini vs DeepSeek r1 3:14:31 - NVIDIA 3:18:58 - GPU smuggling 3:25:36 - DeepSeek training on OpenAI data 3:36:04 - AI megaclusters 4:11:26 - Who wins the race to AGI? 4:21:39 - AI agents 4:30:21 - Programming and AI 4:37:49 - Open source 4:47:01 - Stargate 4:54:30 - Future of AI

Lex Fridman

1,153,653 просмотров • 1 год назад

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below
1:06

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below

starmex

93,086 просмотров • 1 месяц назад

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇
2:28

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

YanXbt

45,809 просмотров • 1 месяц назад

QACE Dynamics | Inside the Making of the Robotics Lab A first look at the core setup behind QACE. Three Jetson Orin NX based QARC units, an Intel mini system, and a firewall are now active as part of the infrastructure powering the decentralised robotics lab. The QACE dApp is already connected to these systems, running live simulations and processing autonomy workloads directly on them. These NVIDIA-powered edge units serve as the backbone for real-time AI inference, multi-sensor processing, and distributed control inside the QACE ecosystem. Very soon, AGVs, robotic arms, and vision systems will be connected to this network as we move toward a live, fully integrated setup. Stay tuned for the next video where we show the robots running on this infrastructure. #QACE #RoboticsAI #EdgeAI #QARC #RoboticsLab #Qognix
0:32

QACE Dynamics | Inside the Making of the Robotics Lab A first look at the core setup behind QACE. Three Jetson Orin NX based QARC units, an Intel mini system, and a firewall are now active as part of the infrastructure powering the decentralised robotics lab. The QACE dApp is already connected to these systems, running live simulations and processing autonomy workloads directly on them. These NVIDIA-powered edge units serve as the backbone for real-time AI inference, multi-sensor processing, and distributed control inside the QACE ecosystem. Very soon, AGVs, robotic arms, and vision systems will be connected to this network as we move toward a live, fully integrated setup. Stay tuned for the next video where we show the robots running on this infrastructure. #QACE #RoboticsAI #EdgeAI #QARC #RoboticsLab #Qognix

Qace Dynamics

10,191 просмотров • 8 месяцев назад

Access codes will go out tomorrow via welcome emails. API status updates and full API access will follow on Friday. HdeAPoHivsm9MZfeY5tW7apJEprc8Fs594bWmnzfpump The $ICPX website has been rebuilt from the ground up and it reflects exactly where this protocol is headed. The new site is the gateway to decentralised compute powered by Nvidia and Google GPU cloud partner programs, meaning whenever you rent a GPU for a job, it is always available. No downtime, no waitlists. Enterprise grade H100s, H200s and RTX 4090s. Accessible to anyone, at a fraction of what centralised providers charge. Pay with $ICPX tokens and get immediate access to serious compute power. Stake $ICPX to unlock deeper discounts and watch your costs drop over time the more committed you are to the network. This is what pay-per-job decentralised compute actually looks like in practice. Full control over training and running your models, with a lean 0.25% protocol fee managed by multisig. Open-source, immutable, and formally verified with Kani. $
0:35

Access codes will go out tomorrow via welcome emails. API status updates and full API access will follow on Friday. HdeAPoHivsm9MZfeY5tW7apJEprc8Fs594bWmnzfpump The $ICPX website has been rebuilt from the ground up and it reflects exactly where this protocol is headed. The new site is the gateway to decentralised compute powered by Nvidia and Google GPU cloud partner programs, meaning whenever you rent a GPU for a job, it is always available. No downtime, no waitlists. Enterprise grade H100s, H200s and RTX 4090s. Accessible to anyone, at a fraction of what centralised providers charge. Pay with $ICPX tokens and get immediate access to serious compute power. Stake $ICPX to unlock deeper discounts and watch your costs drop over time the more committed you are to the network. This is what pay-per-job decentralised compute actually looks like in practice. Full control over training and running your models, with a lean 0.25% protocol fee managed by multisig. Open-source, immutable, and formally verified with Kani. $

ICPX Protocol

32,161 просмотров • 27 дней назад

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones
1:37

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones

@levelsio

261,352 просмотров • 2 лет назад

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:
0:54

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

NVIDIA AI Developer

100,506 просмотров • 11 месяцев назад

🚨 CHINA'S AI PLAYBOOK ISN'T TO BEAT OPENAI AND ANTHROPIC. IT'S TO MAKE THEM IRRELEVANT BY MAKING INTELLIGENCE FREE. Chinese labs are giving away frontier-level models for free. Zhipu's GLM-5 already beats Claude Opus 4.5 and Gemini 3.0 Pro on key benchmarks. DeepSeek, Qwen, and Kimi round out 4 of the top 5 open-weight models globally, all released under open licenses anyone can use commercially. The real weapon isn't the models, it's the cost to run them. Chinese provinces like Gansu, Guizhou, and Inner Mongolia are cutting data center power bills by up to 50%. DeepSeek trained its R1 model for around $6 million, compared to roughly $100 million for GPT-4. The remaining blocker is chips. US export controls still cut China off from Nvidia's best hardware. But Zhipu already trained a full frontier model entirely on Huawei's Ascend chips, no Nvidia involved. Huawei's next-gen Atlas 950 cluster, launching late 2026, claims 6.7 times the compute of Nvidia's planned NVL144 systems. If Huawei closes the chip gap while China keeps giving away free, near frontier models running on subsidized power. The entire business model OpenAI and Anthropic are built on, charging hundreds of billions in aggregate revenue for access to intelligence, stops making sense. Why pay premium prices for marginal capability gains when a free alternative running on cheap compute gets you 90% of the way there.
0:28

🚨 CHINA'S AI PLAYBOOK ISN'T TO BEAT OPENAI AND ANTHROPIC. IT'S TO MAKE THEM IRRELEVANT BY MAKING INTELLIGENCE FREE. Chinese labs are giving away frontier-level models for free. Zhipu's GLM-5 already beats Claude Opus 4.5 and Gemini 3.0 Pro on key benchmarks. DeepSeek, Qwen, and Kimi round out 4 of the top 5 open-weight models globally, all released under open licenses anyone can use commercially. The real weapon isn't the models, it's the cost to run them. Chinese provinces like Gansu, Guizhou, and Inner Mongolia are cutting data center power bills by up to 50%. DeepSeek trained its R1 model for around $6 million, compared to roughly $100 million for GPT-4. The remaining blocker is chips. US export controls still cut China off from Nvidia's best hardware. But Zhipu already trained a full frontier model entirely on Huawei's Ascend chips, no Nvidia involved. Huawei's next-gen Atlas 950 cluster, launching late 2026, claims 6.7 times the compute of Nvidia's planned NVL144 systems. If Huawei closes the chip gap while China keeps giving away free, near frontier models running on subsidized power. The entire business model OpenAI and Anthropic are built on, charging hundreds of billions in aggregate revenue for access to intelligence, stops making sense. Why pay premium prices for marginal capability gains when a free alternative running on cheap compute gets you 90% of the way there.

The Macro Paper

71,111 просмотров • 15 дней назад

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!
0:42

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!

Jiaxuan You

58,144 просмотров • 6 месяцев назад