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.

Updates coming to omarchy: - multiple gpu configs - more models - track your local usage

0xSero

67,551 subscribers

28,510 views • 2 days ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

12 Comments

Karanbir Singh2 days ago

What makes this all omarchy specific?

navigating...2 days ago

the omarchy propaganda is getting to me. is it time I give up on my ubuntu22.04 on xps and switch?

0xSero2 days ago

Bro you’re free to do what you want I’m getting into it

NicKlaus2 days ago

multi-gpu + local usage tracking is the boring ship. agent desktops without that are just a theme with a chat box

Bom Tombadil1 day ago

Nice. Hopefully some AMD options soon now that Halo machines are popping off. Get yourself ready for when the RTX Spark laptops finally drop this fall.

Maximus Hodlius1 day ago

YESSSSSSS

Knowix2 days ago

got to play around with this one, are the updates live yet?

garyyoung1 day ago

We should have a blockchain to trade LLM access and get paid in stablecoins. The SaaS model of current LLM aggregators is old and clunky.

𝔹𝔸𝔹𝔸 𝕁𝔸𝔾𝔸1 day ago

Too cool.

0xQuan2 days ago

ohhh this is so needed, I was just building this

Crystal Phantom2 days ago

Tracking local usage directly removes the guesswork when balancing workloads across multiple GPUs.

gray1 day ago

usage tracking is the part that matters. tok/s demos are easy. i want hours of local agent work, which model, peak vram, and where it failed.

Related Videos

Local AI will be right in your OS Omarchy, PR up soon.

Local AI will be right in your OS Omarchy, PR up soon.

0xSero

55,753 views • 18 days ago

Omarchy will be a beautiful home. Local AI

Omarchy will be a beautiful home. Local AI

0xSero

27,805 views • 1 day ago

Here's Qwen3.8-27B Runs on any macbook/gpu with 24gb or more I gave it an hour of video, and told it to find the latest session with claude where it helped me make edit yesterdays video and create the thumbnail Running on Openrouter, big models do first Small models follow

Here's Qwen3.8-27B Runs on any macbook/gpu with 24gb or more I gave it an hour of video, and told it to find the latest session with claude where it helped me make edit yesterdays video and create the thumbnail Running on Openrouter, big models do first Small models follow

0xSero

23,510 views • 12 days ago

Very nice Claude Code dashboard for power users to track every request. - Use multiple subscriptions with load balance to switch accounts - Set models for subagents - Track latency, token usage, and costs in real-time - Full request logging and error traces (Link below!)

Very nice Claude Code dashboard for power users to track every request. - Use multiple subscriptions with load balance to switch accounts - Set models for subagents - Track latency, token usage, and costs in real-time - Full request logging and error traces (Link below!)

Ian Nuttall

110,838 views • 1 year ago

CSS Studio. A visual editor in your browser that streams updates to your local AI agent. Your browser, your agent, your source code. Coming soon.

CSS Studio. A visual editor in your browser that streams updates to your local AI agent. Your browser, your agent, your source code. Coming soon.

Motion

56,094 views • 5 months ago

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.

0xSero

32,853 views • 5 months ago

Deploy a GPU node on NodeAI in minutes. 1. Head to 2. Choose a template (SSH, Oobabooga, more coming) 3. Select your GPU server 4. Hit Deploy and monitor from your dashboard Build faster. Ship smarter. #AI #GPU #NODEAI #DePIN

Deploy a GPU node on NodeAI in minutes. 1. Head to 2. Choose a template (SSH, Oobabooga, more coming) 3. Select your GPU server 4. Hit Deploy and monitor from your dashboard Build faster. Ship smarter. #AI #GPU #NODEAI #DePIN

Node AI | $GPU

26,668 views • 1 year ago

Exo No more worrying about it. Best model best config best harness for your hardware based on local . ai benchmarks just: exo run

Exo No more worrying about it. Best model best config best harness for your hardware based on local . ai benchmarks just: exo run

0xSero

43,386 views • 2 months ago

Better annotating screenshot tool coming to Omarchy Quattro.

Better annotating screenshot tool coming to Omarchy Quattro.

tobi lutke

381,598 views • 1 month ago

Back to building my Minecraft-inspired voxel game for the Dreamcast! Development's back on track. Stay tuned for more updates in the coming weeks.

Back to building my Minecraft-inspired voxel game for the Dreamcast! Development's back on track. Stay tuned for more updates in the coming weeks.

A Flock of Meese

39,584 views • 1 year ago

After an all-nighter, we got the first app working with Omagrid: OpenCode. Just boot into Omarchy. DeepSeek + Qwen are already there for all your apps and agents. It’s that simple. Want early access? DM me! PS: Omagrid is a P2P network. More Omarchy machines, more models.

After an all-nighter, we got the first app working with Omagrid: OpenCode. Just boot into Omarchy. DeepSeek + Qwen are already there for all your apps and agents. It’s that simple. Want early access? DM me! PS: Omagrid is a P2P network. More Omarchy machines, more models.

Dee

125,624 views • 10 days ago

I figured out how to get Claude working anywhere without extra usage and technically in line with Anthropic's TOS. I don't recommend you adopt this, might get you banned but as you can see, no errors, no extra usage consumed. The point of this is to demonstrate futility.

I figured out how to get Claude working anywhere without extra usage and technically in line with Anthropic's TOS. I don't recommend you adopt this, might get you banned but as you can see, no errors, no extra usage consumed. The point of this is to demonstrate futility.

0xSero

51,550 views • 5 months ago

"I don't have a GPU" is officially dead. VS Code now connects directly to Google Colab. → You get a free T4 GPU inside your editor. → Your local files. Their compute.

"I don't have a GPU" is officially dead. VS Code now connects directly to Google Colab. → You get a free T4 GPU inside your editor. → Your local files. Their compute.

Simplifying AI

619,561 views • 8 months ago

"My token usage is probably down 30x compared to before.” Tim Davis, Co-Founder & President Modular on why he builds AI tooling locally first: “Token usage is incredibly expensive. If you just throw your whole codebase into a model, you’re constantly uploading everything and burning hundreds of thousands or millions of tokens.” “Instead, you can build local representations of your codebase using embedding models. They’re more context-aware, and you only need to send much smaller summaries to models like Claude, Codex, or Gemini.” “That gives you enormous efficiency gains. My token usage is probably down 30x compared to before.”

"My token usage is probably down 30x compared to before.” Tim Davis, Co-Founder & President Modular on why he builds AI tooling locally first: “Token usage is incredibly expensive. If you just throw your whole codebase into a model, you’re constantly uploading everything and burning hundreds of thousands or millions of tokens.” “Instead, you can build local representations of your codebase using embedding models. They’re more context-aware, and you only need to send much smaller summaries to models like Claude, Codex, or Gemini.” “That gives you enormous efficiency gains. My token usage is probably down 30x compared to before.”

Forward Future

65,173 views • 7 months ago

The Canes are coming in HOT. 🔥 More than 27 game watch parties are gearing up across the country. Find your local Canes Community and get ready to cheer on the Hurricanes as they take on Texas A&M. Visit for updates on your local game watch party.

The Canes are coming in HOT. 🔥 More than 27 game watch parties are gearing up across the country. Find your local Canes Community and get ready to cheer on the Hurricanes as they take on Texas A&M. Visit for updates on your local game watch party.

University of Miami Alumni Association

20,079 views • 9 months ago

Here's how I make rags out of all my data with LOCAL MODELS ONLY GLM-4.7-Flash turns all my anthropic chats to a rag, and makes a skill to use it from anywhere. This video has the whole process. excuse the annoying watermark, I wanted to speed the video up

Here's how I make rags out of all my data with LOCAL MODELS ONLY GLM-4.7-Flash turns all my anthropic chats to a rag, and makes a skill to use it from anywhere. This video has the whole process. excuse the annoying watermark, I wanted to speed the video up

0xSero

20,952 views • 7 months ago

Add extra GPU power to your laptop or mini PC — without rebuilding. The MINISFORUM DEG2 eGPU Dock supports Thunderbolt 5 and OCuLink (PCIe 4.0 ×4), letting one desktop GPU power multiple devices. 🔗 Learn more: #MINISFORUM #DEG2 #eGPU #ExternalGPU #Thunderbolt5 #OCuLink

Add extra GPU power to your laptop or mini PC — without rebuilding. The MINISFORUM DEG2 eGPU Dock supports Thunderbolt 5 and OCuLink (PCIe 4.0 ×4), letting one desktop GPU power multiple devices. 🔗 Learn more: #MINISFORUM #DEG2 #eGPU #ExternalGPU #Thunderbolt5 #OCuLink

MINISFORUM Official

95,098 views • 8 months ago

August traditionally brings the hottest weather of the year to Alabama. Alabama Power has some great tools to set alerts and track your daily energy usage. With a better understanding of how your home uses energy, you can make small adjustments to stay on track and keep your bill more consistent month to month.

August traditionally brings the hottest weather of the year to Alabama. Alabama Power has some great tools to set alerts and track your daily energy usage. With a better understanding of how your home uses energy, you can make small adjustments to stay on track and keep your bill more consistent month to month.

James Spann

17,892 views • 29 days ago

We've added Workspaces to the Anthropic Console. Workspaces let you easily manage multiple Claude deployments. You can also set custom spend or rate limits, group API keys, track usage by project, and control access with user roles. Read more:

We've added Workspaces to the Anthropic Console. Workspaces let you easily manage multiple Claude deployments. You can also set custom spend or rate limits, group API keys, track usage by project, and control access with user roles. Read more:

Anthropic

165,868 views • 2 years ago