正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

📢 Inference is ON 😎 Run any AI model on dedicated GPU hardware, starting today. The GPU is yours while you're on it, the full price is displayed before you commit, and the model is whatever you bring from Hugging Face. Wild concept, we know! 👇

Ocean Network

1,912 subscribers

459,563 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

17 条评论

Ocean Network 的头像

Ocean Network2 个月前

H200 at $2.16/hr. Resources bundled for you. Before your session starts, you see exactly what you're booking and what it costs. The node claims your session window upfront, so what you see is what you pay, no shared resources and no billing surprises. That's it.

Ocean Network 的头像

Ocean Network2 个月前

Four ways to get running: →Curated: pre-tuned model and engine combos, ready in minutes →Custom: any Hugging Face model, every config flag exposed →Services: ComfyUI, JupyterLab, Open WebUI, Open Code →Templates: skip setup, launch into video gen and more Try it:

Ocean Network 的头像

Ocean Network2 个月前

Once you're live, you get container logs, a countdown on your paid window, and edit-and-relaunch so you can swap the model or engine without losing your endpoint or the time you booked. Every model exposes an @OpenAI-compatible endpoint, so your existing SDKs drop straight in.

Ocean Network 的头像

Ocean Network2 个月前

That product video you keep putting off? Write a prompt, pick a Template, and it's generating. A good quality 30-second clip takes roughly 20 minutes. Break down the H200 rate and it comes to about $0.72. Book it, run it, own it:

Ocean Network 的头像

Ocean Network2 个月前

Your first 6 hours of H200 inference are on us Complimentary tokens, no strings, just you and the hardware Claim yours and show us what you can make with it. Let's turn inference ON together!

Richard 的头像

Richard2 个月前

@huggingface you guys really cooked here 🤯 time to try it out

EmmyTruz 的头像

EmmyTruz2 个月前

@huggingface Giving the first 6 hours for free is wild I am checking this out right away

GODEN 的头像

GODEN2 个月前

@huggingface Testing this ASAP 🔥 this was worth the wait 🤯

Himas 的头像

Himas2 个月前

@huggingface Finally, this will save me a ton of money on AI tokens

Cranky Killjoy 的头像

Cranky Killjoy2 个月前

@huggingface I definitely need to put this to the test 👀

ΞLB𝐔𝐌𝐏𝐘 的头像

ΞLB𝐔𝐌𝐏𝐘2 个月前

@huggingface H200 inference at $2.16/hr beats what most clouds won't even quote you. Devs can finally run serious models without the bill killing the vibe.

Florida crocodile🍊🐊 的头像

Florida crocodile🍊🐊2 个月前

@huggingface Wow, new stage of efficiency is here!

𝓣𝓪𝓼𝓱𝓪 的头像

𝓣𝓪𝓼𝓱𝓪2 个月前

@huggingface This is top-notch H200 for $2.16/hr + your own session + no surprise billing. Yeah, inference just got a serious upgrade 🔥

Fairu ✳️ 的头像

Fairu ✳️2 个月前

@huggingface Most GPU marketplaces sell vibes. This one is selling a booked window and a bill you can read. That’s the part worth testing.

Lilita 的头像

Lilita2 个月前

@huggingface Running your own models on dedicated GPUs feels really practical

What1slove 的头像

What1slove2 个月前

@huggingface awesome news, wanna try it

Emmanuel 的头像

Emmanuel2 个月前

@huggingface This is exceptional. Time to start running models on GPUs Well-done Ocean Network

相关视频

You need to know 4 things to run local AI on your own machine: 1) The model is the brain file. Gemma, Llama, Mistral, Qwen, Phi. 2) The warehouse is where you find the model. Hugging Face. 3) The software is what runs the model. LM Studio for the first try, Ollama when you build apps. 4) The workflow is the product you make from the other three. The size of the model decides the hardware: - 2B to 4B for phones and small tasks - 12B for the middle ground - 26B to 31B for a workstation Quantization compresses the model until it fits on a normal machine: - Q4 is easier to run - Q8 keeps more quality, but it needs more memory Q4 costs you a little quality but it saves you a $5,000 workstation. Start on the spare laptop from 2021. Open Hugging Face and read one model card slowly.

You need to know 4 things to run local AI on your own machine: 1) The model is the brain file. Gemma, Llama, Mistral, Qwen, Phi. 2) The warehouse is where you find the model. Hugging Face. 3) The software is what runs the model. LM Studio for the first try, Ollama when you build apps. 4) The workflow is the product you make from the other three. The size of the model decides the hardware: - 2B to 4B for phones and small tasks - 12B for the middle ground - 26B to 31B for a workstation Quantization compresses the model until it fits on a normal machine: - Q4 is easier to run - Q8 keeps more quality, but it needs more memory Q4 costs you a little quality but it saves you a $5,000 workstation. Start on the spare laptop from 2021. Open Hugging Face and read one model card slowly.

The Startup Ideas Podcast (SIP) 🧃

10,947 次观看 • 2 个月前

Understanding GPUs will change your AI Engineering journey beyond agents and LLM. Rise of LLMs and deep learning introduced dedicated GPU hardware which serves your models for training and inference. You don't need to start with C++, CUDA, and Maths, but: > Components of a GPU and roles > How a token flows through hardware > Compute vs memory, the two limits > What FLOPS means in practice > Training vs inference hardware needs > What is CUDA Kernels > Calculating GPU memory from model size > Quantization to fit bigger models > Multi-GPU and splitting large models Hugging Face has the feature of calculating FLOps and recommending GPUs for your use case. You must explore. In terms of inference engineering, GPU understanding are much helpful your platform performance and handling multiple requests. Read this article for complete breakdown of GPUs for AI Engineers doesn't require any pre-requisite.

Understanding GPUs will change your AI Engineering journey beyond agents and LLM. Rise of LLMs and deep learning introduced dedicated GPU hardware which serves your models for training and inference. You don't need to start with C++, CUDA, and Maths, but: > Components of a GPU and roles > How a token flows through hardware > Compute vs memory, the two limits > What FLOPS means in practice > Training vs inference hardware needs > What is CUDA Kernels > Calculating GPU memory from model size > Quantization to fit bigger models > Multi-GPU and splitting large models Hugging Face has the feature of calculating FLOps and recommending GPUs for your use case. You must explore. In terms of inference engineering, GPU understanding are much helpful your platform performance and handling multiple requests. Read this article for complete breakdown of GPUs for AI Engineers doesn't require any pre-requisite.

Karan🧋

33,453 次观看 • 1 个月前

This is HUGE, Hugging Face just shipped Inference Providers on the Hub Partnering with Together AI, @FAL, Replicate and SambaNova! Starting today you can access thousands of Models like DeepSeek R1, Llama, Flux, Whisper, and more Directly from Hugging Face!

This is HUGE, Hugging Face just shipped Inference Providers on the Hub Partnering with Together AI, @FAL, Replicate and SambaNova! Starting today you can access thousands of Models like DeepSeek R1, Llama, Flux, Whisper, and more Directly from Hugging Face!

AK

177,217 次观看 • 1 年前

We built Curie, colibrì’s own model: 17B parameters, 33 tokens/s on a single CPU core. No GPU. Trained from scratch on a standard laptop. Written in C. Weights on SSD. An engine and a model designed together for the hardware you already own. Early alpha.This is just the beginning

We built Curie, colibrì’s own model: 17B parameters, 33 tokens/s on a single CPU core. No GPU. Trained from scratch on a standard laptop. Written in C. Weights on SSD. An engine and a model designed together for the hardware you already own. Early alpha.This is just the beginning

JustVugg

51,567 次观看 • 2 个月前

We spoke with Modal CEO Erik Bernhardsson about the "broken model" of massive GPU reservations. He says "hype" led companies to waste money on underutilized hardware. Modal's platform ensures you only pay for the GPU time you actually run.

We spoke with Modal CEO Erik Bernhardsson about the "broken model" of massive GPU reservations. He says "hype" led companies to waste money on underutilized hardware. Modal's platform ensures you only pay for the GPU time you actually run.

TBPN

34,361 次观看 • 1 年前

I trained a small model to do syntax highlighting in the browser with GPU. Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax). It is experimental and built for learning!

I trained a small model to do syntax highlighting in the browser with GPU. Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax). It is experimental and built for learning!

Shu

801,298 次观看 • 2 个月前

This is cool, Elon Musk says SpaceX will allow their customers to use any GPU or TPU they want in SpaceX AI Satellites. "We do intend with our SpaceX AI Satellites to allow people to put whatever GPU or TPU they want. So Nvidia GPUS can be put on it, Google TPUs can be put on it, Amazon Trainium, or any other chips people want to put on. It will be such that you can run anyone’s AI, hardware or software on the SpaceX AI Satellites." An open platform design is so smart.

This is cool, Elon Musk says SpaceX will allow their customers to use any GPU or TPU they want in SpaceX AI Satellites. "We do intend with our SpaceX AI Satellites to allow people to put whatever GPU or TPU they want. So Nvidia GPUS can be put on it, Google TPUs can be put on it, Amazon Trainium, or any other chips people want to put on. It will be such that you can run anyone’s AI, hardware or software on the SpaceX AI Satellites." An open platform design is so smart.

Nic Cruz Patane

115,448 次观看 • 5 个月前

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,854 次观看 • 4 个月前

$TSLA 🚨 Model Y L launched in Korea today is the cheapest than all countries on sale. It costs around $43,000 before you get the subsidy. • Starting price : 64,990,000 WON~ Korea is now a completely strategic location.

$TSLA 🚨 Model Y L launched in Korea today is the cheapest than all countries on sale. It costs around $43,000 before you get the subsidy. • Starting price : 64,990,000 WON~ Korea is now a completely strategic location.

Tsla Chan

56,948 次观看 • 7 个月前

Physical AI gets so complicated at times ... We just launched the easiest way to run frontier physical AI models on your robots - the UI can't get any simpler: I want to run a on a to No GPU, pure real-time inference over the cloud. Live now at:

Physical AI gets so complicated at times ... We just launched the easiest way to run frontier physical AI models on your robots - the UI can't get any simpler: I want to run a on a to No GPU, pure real-time inference over the cloud. Live now at:

Chris Yoo ⚡ CoRL

16,467 次观看 • 29 天前

Comparing hardware on InferenceX just got a massive upgrade. Our new changelog update lets you compare every change for any gpu all on the same chart. Just select any model and GPU config, then select a date range and hit 'Add All to Chart' to instantly see every software update and performance shift across the full date range.

Comparing hardware on InferenceX just got a massive upgrade. Our new changelog update lets you compare every change for any gpu all on the same chart. Just select any model and GPU config, then select a date range and hit 'Add All to Chart' to instantly see every software update and performance shift across the full date range.

SemiAnalysis

19,821 次观看 • 7 个月前

H100s, Blackwell & the GPU Revolution GPU supply is tight and demand is surging. We aggregate thousands of H100s, A100s, L40S, MI300X & more into one on-demand pool. One click and you’re training LLMs or vision models—no sticker shock. Skip the shortage. Build on NodeAI today. ⚡️ #AI #GPU #NODEAI

H100s, Blackwell & the GPU Revolution GPU supply is tight and demand is surging. We aggregate thousands of H100s, A100s, L40S, MI300X & more into one on-demand pool. One click and you’re training LLMs or vision models—no sticker shock. Skip the shortage. Build on NodeAI today. ⚡️ #AI #GPU #NODEAI

Node AI | $GPU

12,982 次观看 • 1 年前

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

Uomi

19,017 次观看 • 4 个月前

Just launched #CES2026, the new open-source NVIDIA Nemotron Speech ASR model is here to solve latency drift and redundant compute. Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up to 3x more throughput on your GPU. 🤗 Read the technical blog with real-world results from Daily and Modal on Hugging Face:

Just launched #CES2026, the new open-source NVIDIA Nemotron Speech ASR model is here to solve latency drift and redundant compute. Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up to 3x more throughput on your GPU. 🤗 Read the technical blog with real-world results from Daily and Modal on Hugging Face:

NVIDIA AI Developer

138,518 次观看 • 10 个月前

Vemana is out. It's a 278M Telugu model we trained from scratch, live, on one GPU, for about $69. And I think the result surprised even me: on new Telugu Wikipedia pages it beats every open base model under 1B that we tested, including nanochat-telugu-560M, which is twice its size. The weights, every checkpoint and the eval code are public. And you can run it right in your browser, on your own device, nothing gets sent anywhere.

Vemana is out. It's a 278M Telugu model we trained from scratch, live, on one GPU, for about $69. And I think the result surprised even me: on new Telugu Wikipedia pages it beats every open base model under 1B that we tested, including nanochat-telugu-560M, which is twice its size. The weights, every checkpoint and the eval code are public. And you can run it right in your browser, on your own device, nothing gets sent anywhere.

Jitesh K Prasad

62,691 次观看 • 17 天前

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.

👋 Jan

40,207 次观看 • 1 年前

We built Talos - a full CNN inference engine running directly on silicon. Every multiply, buffer, and data path lives as real digital logic on the FPGA. This is what deep learning looks like when the model becomes hardware👇

We built Talos - a full CNN inference engine running directly on silicon. Every multiply, buffer, and data path lives as real digital logic on the FPGA. This is what deep learning looks like when the model becomes hardware👇

luthira

92,700 次观看 • 8 个月前

Meta president Dina Powell McCormick on AI safety and guardrails: "Safety is not something you think about after you build the model. It is embedded in the model."

Meta president Dina Powell McCormick on AI safety and guardrails: "Safety is not something you think about after you build the model. It is embedded in the model."

CSPAN

13,032 次观看 • 1 个月前

We made the first AI model you can have a realistic conversation with that was trained entirely on speech! Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs. This is a GPT3 moment for speech.

We made the first AI model you can have a realistic conversation with that was trained entirely on speech! Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs. This is a GPT3 moment for speech.

Ragavan Thurairatnam

4,655,184 次观看 • 21 天前