Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I rebuilt much of my OpenClaw stack to run on local models. Getting this right is harder than it looks. I partnered with @NVIDIA_AI_PC to show you exactly how my hybrid local/hosted architecture works:

MatthewBerman's profile picture

Matthew Berman

124,256 subscribers

167,182 Aufrufe • vor 3 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:
19:14

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Alex Finn

573,553 Aufrufe • vor 5 Monaten

OpenClaw is the single most important software release ever It is critical you use it to its max potential In this video I cover EVERY aspect of OpenClaw you need to know From set up to use cases to local models. EVERYTHING This is the only OpenClaw video you'll ever need:
44:07

OpenClaw is the single most important software release ever It is critical you use it to its max potential In this video I cover EVERY aspect of OpenClaw you need to know From set up to use cases to local models. EVERYTHING This is the only OpenClaw video you'll ever need:

Alex Finn

226,158 Aufrufe • vor 4 Monaten

Stop using frontier models for your entire OpenClaw stack. It's expensive and wastes your quota. The first step is identifying which use cases CAN be moved to local models. Here's how I do that:
0:33

Stop using frontier models for your entire OpenClaw stack. It's expensive and wastes your quota. The first step is identifying which use cases CAN be moved to local models. Here's how I do that:

Matthew Berman

58,095 Aufrufe • vor 3 Monaten

🚨 BREAKING: Scott Presler is getting massive support after launching a RUN FOR OFFICE in Pennsylvania — starting out local with Beaver County State GOP Committeeman "I want to start local and do it the right way. I want to help my community and make sure we win this November in Pennsylvania and defeating Governor Shapiro." "It's on my heart to help my local community." LET'S GO! You'll crush it, ThePersistence! 🇺🇸🔥 Dr. Drew
2:27

🚨 BREAKING: Scott Presler is getting massive support after launching a RUN FOR OFFICE in Pennsylvania — starting out local with Beaver County State GOP Committeeman "I want to start local and do it the right way. I want to help my community and make sure we win this November in Pennsylvania and defeating Governor Shapiro." "It's on my heart to help my local community." LET'S GO! You'll crush it, ThePersistence! 🇺🇸🔥 Dr. Drew

Eric Daugherty

82,045 Aufrufe • vor 5 Monaten

Do you see what's happening? Local AI is getting smarter. It's Opus 4.5 level Hardware that hosts those models are flying off the shelf Your window to host local models is shrinking In this video I cover EVERYTHING local AI models and how to host your own, even on Mac Minis:
21:26

Do you see what's happening? Local AI is getting smarter. It's Opus 4.5 level Hardware that hosts those models are flying off the shelf Your window to host local models is shrinking In this video I cover EVERYTHING local AI models and how to host your own, even on Mac Minis:

Alex Finn

55,253 Aufrufe • vor 4 Monaten

This is exactly how I was taught how to parallel park my car when I was a kid! It works!
0:39

This is exactly how I was taught how to parallel park my car when I was a kid! It works!

Kathleen Winchell ❤️🤍💙🇺🇸🇺🇸

237,777 Aufrufe • vor 8 Monaten

this is so much harder than it looks but I want to master it so badly 😭
0:21

this is so much harder than it looks but I want to master it so badly 😭

Sassington, M.C.

1,183,083 Aufrufe • vor 1 Jahr

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.
2:15

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 Aufrufe • vor 4 Monaten

I'm blown away. Ornith-1.0 35b is the best local model I've ever run that doesn't require 200GB+ of RAM Incredible at coding According to my tests it's both smarter and faster than Qwen 3.6 Plus it runs like a dream on a DGX Spark Here's how I'm using it: I have it running every hour and looping through different parts of my Henry Intelligent Machines codebase It looks for security vulnerabilities Any vulnerabilities it finds, it writes a report with the fix Then once a day another loop I have running in Codex reads the report with all the security bugs and verifies, then fixes I also have it once a day going through a reviewing all my open PRs Local models running on loops 24/7 is the future. I promise you What's becoming possible today with local models is truly mind blowing
0:23

I'm blown away. Ornith-1.0 35b is the best local model I've ever run that doesn't require 200GB+ of RAM Incredible at coding According to my tests it's both smarter and faster than Qwen 3.6 Plus it runs like a dream on a DGX Spark Here's how I'm using it: I have it running every hour and looping through different parts of my Henry Intelligent Machines codebase It looks for security vulnerabilities Any vulnerabilities it finds, it writes a report with the fix Then once a day another loop I have running in Codex reads the report with all the security bugs and verifies, then fixes I also have it once a day going through a reviewing all my open PRs Local models running on loops 24/7 is the future. I promise you What's becoming possible today with local models is truly mind blowing

Alex Finn

314,695 Aufrufe • vor 1 Monat

I isolated this vocal with my local AI for trining (it has nothing to do with music models) and I am taken back by these falsettos. No autotune.
2:46

I isolated this vocal with my local AI for trining (it has nothing to do with music models) and I am taken back by these falsettos. No autotune.

Brian Roemmele

21,563 Aufrufe • vor 3 Monaten

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below
16:10

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,245 Aufrufe • vor 4 Monaten

“Coffee with Kenny” Local racer asked me how I made it to NASCAR ? MY STORY 😳
17:56

“Coffee with Kenny” Local racer asked me how I made it to NASCAR ? MY STORY 😳

Kenny Wallace

15,178 Aufrufe • vor 1 Jahr

I have an AI employee doing work for me 24/7 for basically free You NEED to set this up It's Hermes Agent powered by local models on a @NVIDIA_AI_PC DGX Spark In this video I cover how to set up Hermes, load in Qwen 3.6, and have it work 24/7. NO experience required
24:06

I have an AI employee doing work for me 24/7 for basically free You NEED to set this up It's Hermes Agent powered by local models on a @NVIDIA_AI_PC DGX Spark In this video I cover how to set up Hermes, load in Qwen 3.6, and have it work 24/7. NO experience required

Alex Finn

93,249 Aufrufe • vor 2 Monaten

“I am a Jedi. Like my father before me” still hits so much harder than it has any right to
0:55

“I am a Jedi. Like my father before me” still hits so much harder than it has any right to

Armand Domalewski

20,702 Aufrufe • vor 1 Jahr

Here's my current tech stack, why I'm using it. And what I think is happening in the local AI scene. Unfortunately I don't like organising myself so you'll have to put up with my rambling (:
25:42

Here's my current tech stack, why I'm using it. And what I think is happening in the local AI scene. Unfortunately I don't like organising myself so you'll have to put up with my rambling (:

0xSero

23,545 Aufrufe • vor 3 Monaten

How to have your Openclaw install the new Qwen 3.5-9b Local LLM in 1 minute This came out TODAY and is one of the only local models you can run on a 16GB Mac Mini Will be testing and making some videos this week, look out for that (check below for some tests for now)
1:04

How to have your Openclaw install the new Qwen 3.5-9b Local LLM in 1 minute This came out TODAY and is one of the only local models you can run on a 16GB Mac Mini Will be testing and making some videos this week, look out for that (check below for some tests for now)

ashen

63,977 Aufrufe • vor 5 Monaten

This is why I stopped going to my local casino…
0:25

Sensitive content

This is why I stopped going to my local casino…

ClubWPT Gold

48,643 Aufrufe • vor 11 Monaten

I’m so honored to run this scheme, Ryan meant so much to my development racing late models out west and with this year being a “throwback to your roots” theme I knew exactly who I had to throwback to
1:28

I’m so honored to run this scheme, Ryan meant so much to my development racing late models out west and with this year being a “throwback to your roots” theme I knew exactly who I had to throwback to

Dean Thompson

12,912 Aufrufe • vor 2 Jahren

🐶: I only want to see you, no, I want to show you to everyone 🐱: No limit, fill it with the taste of love I'll run to you 🐱: How beautiful 🐶: Because you're my headliner, my headliner singing those lines right after one another is so goodddd to hear 🥹🥹🥹🥹🥹
0:23

🐶: I only want to see you, no, I want to show you to everyone 🐱: No limit, fill it with the taste of love I'll run to you 🐱: How beautiful 🐶: Because you're my headliner, my headliner singing those lines right after one another is so goodddd to hear 🥹🥹🥹🥹🥹

🐈🐕

46,769 Aufrufe • vor 2 Jahren

OpenClaw is the single most important software release of all time It is critical you use it to its max potential In this video I cover EVERY aspect of OpenClaw you need to know From use cases to models to Mac Minis. EVERYTHING This is the only OpenClaw video you'll ever need
46:47

OpenClaw is the single most important software release of all time It is critical you use it to its max potential In this video I cover EVERY aspect of OpenClaw you need to know From use cases to models to Mac Minis. EVERYTHING This is the only OpenClaw video you'll ever need

Alex Finn

71,084 Aufrufe • vor 3 Monaten