localsonly

@AlexFinn What is your favorite models for DGX Spark? I have one coming next week.

I don't care what kind of hardware you have, you should be running local models It will save you a ton on money on OpenClaw and keep your data private Even if you're on the cheapest Mac Mini you can be doing this Here's a complete guide: 1. Download LMStudio 2. Go to your OpenClaw/Hermes and say what kind of hardware you have (computer and memory and storage) 3. Ask what's the best local model you can run on there (probably will be Gemma 4 or Qwen. if you have a big computer, it will be GLM) 4. Ask 'based on what you know about me, what workflows could this open model replace?' 5. Have OpenClaw walk you through downloading the model in LM Studio and setting up the API 6. Ask OpenClaw to start using the new API Boom you're good to go. You just saved money by using local models, have an AI model that is COMPLETELY private and secure on your own device, did something advanced that 99% of people have never done, and have entered the future. If you are on smaller hardware you probably are not going to replace all your AI calls with this, but you could replace smaller workflows which will still save you good money Own your intelligence.

@andyantiles_ What if I’m already in real estate… and she is too?

If you’re making over $250k/yr Retire your wife immediately Not so she can do yoga and Pilates all day But so she can become the family real estate professional With the real estate professional status on your tax returns You’ll be able to claim enormous tax deductions from buying real estate Have your wife quit her job And you’ll secure generational wealth from buying tax deductible, cash flowing real estate My life changed forever when I had my wife quit her corporate job and we started buying a ton of section 8 rental properties Running this playbook till I’m blue in the face

@realEstateTrent @SJFriedl Wait you actually want control about your financial decisions? Makes more sense when you look at the actual principal payments you’re making over the first 5 to 10 years.

@SJFriedl You’re making a different argument. I’m saying it’s better to have the freedom to choose how much you’re paying of; and when, if any.

The blind spots around the home mortgage topic are wild. The people who don’t understand the math behind why being forced to pay down principal monthly is a bad financial move are the exact same people who desperately need that forced structure. So it all works out.

Local AI is not just a toy. Here's what changed this week: 1. An 80B coding model (Qwen3-Coder-Next) now fits on a 64 GB Mac mini. 3B active per token. MoE does the heavy lifting. Going to try and do the CRM run on this. Might be too big. 2. Ollama's MLX preview landed. ~2x decode on Apple Silicon. The bottleneck people kept pointing at is gone. Anything else I missed? Anything worth testing on a 16GB and 64GB Mac Mini?

@JonhernandezIA @nvidia @openclaw Looks good! Adding a GX10 (pretty much DGX Spark). Should be landing Tuesday.

The army is growing! Added the spark from @nvidia to run an @openclaw with gemma 4 local and also run some models for my other claws, image, voice etc.. So far I have One Mac mini with codex as my main work horse named clippy. Another Mac mini with zai gl5.1 he does some specific stuff and is a great backup when clippy has a problem, he can get clippy backup when there is a problem and it's been really a bless as I'm traveling all the time. And now the spark adding to the team... It's quite a journey but loving it... Having your own personalized ultra agentic chatgpt setup is incredible

@0xSero Would a 3090 with my 64GB mini be worth anything? Will probably get a M5 Studio when it comes out. Just debating on getting a 3090 now or waiting.

If you have 5k budget I’d recommend this. A 3090 and a Mac Studio with 256gb

SaaS got away with adding back SBC. Some one is going to figure out the next move: Pay LLM providers in stock instead of cash. Call it “AI R&D.” Add it back to EBITDA. Same cost. Better story.

8/ Updated CRM Scoreboard: Claude Opus 4.6: 24/25 Gemma 4 31B: 23/25 ← new Gemma 4 e4b (9.6 GB): 22/25 Qwen3-Coder 30B: 21/25 Gemma 4 26B: 21/25 Qwen 2.5 Coder 14B: 19/25 The gap is closing faster than most takes on this app will tell you.

7/The catch is real and I'm not going to dress it up. 20 minutes per round means your dev loop is "kick it off, go walk the dog, come back." Not "run it, read the output, iterate." Different workflow. But it's $0 a query, on your hardware, with your data. For a lot of the work I care about, that's the better tradeoff.

"Local models can't keep up with Claude on real coding work." That's what I told myself for months. It's why I left Gemma 4 31B out of the first CRM benchmark. Too slow to bother with. Ran it this week anyway. It came one point short of Opus. Here's what I found. 🧵

@AndrewYang But AI companies are expanding physical office space? Anthropic and OpenAI now over 1M square feet with that space committed for +10 years. They either: 1.) anticipate headcount growth Or 2.) are horrible at planning for the future

What happens when millions of white-collar jobs disappear? blog.andrewyang.com/p/the-end-of-t…

@RandBusiness I’m working on building tests for running real business tasks in local models and consumer machines (Mac mini, DGX Spark, Mac Studio (when it arrives). I want to see what can actually be offloaded in a reliable way. If you have any workflows or tests I should do, let me know!

I believe business owners need to see real examples of how other owners are actually using AI in their business. Then literally just steal it and implement it in your own business Right now in Scalepath, this is what we’re doing. We have an “AI-Use-cases” channel in our slack forum. And ~every 2 weeks we’re doing live demonstrations having members show off exactly what they’ve built. Last week a member demoed his vibe coded Service Titan replacement. He uses it every day in his business. We’re doing as much of this as possible. Being early and “ahead” on AI will drive a ton of value to our members, so we want everyone to share what they’re building. The whole community will prosper. Charles, will you let us demo your stuff next?

@SahilBloom I was just telling my wife it’s sad that some people will never get to enjoy this experience because they are told partying is more fun or you should focus on your career.

Whoever said having a kid was the end of your fun clearly never had a kid.

@SethMoldenhauer This. I’m luckily an early riser too. Gives me 3 hours of me time before my son wakes up. Learn, build and work out. Keeps me sane.

I have an almost 4 year old and a 15 month old. I work full time, am obtaining my master's degree, and work at clinicals multiple days per week. Please understand, I am not perfect and this is not intended to claim this is easy, because it's not. "Advice is a dangerous gift, even from the wise to the wise, and all courses may run ill." With that being said, embrace this time. Your children grow quickly, they need you as a father. Present, attentive, and whole. Understand just how selfish your life was before having children and embrace your current role of raising good children. Change your mindset. Some practical steps: Do a root cause analysis on the areas you're being burned out in. What is causing them? Find quality time with your wife, even if it's only an hour before bed. You fill each other's cups. Focus on getting exercise WITH your children. Take them to the park, go for a run, do bodyweight workouts. Make it a game. Focus on a consistent bedtime. Not only for your children, but for you. Go to bed by 9pm and limit screen time prior. Wake early, before the household. I am up at 0400 5-6 days per week. This is when I do school work before going into work or clinical. If you don't have that, read, play video games, work on your side quest or hobbies. Use this time for you. Audit your life and decide what things bring you joy. Lean into those WITH your children. Be silly. Embrace childhood. Laugh. Play. Be ridiculous. Understand that as the man of the house, as the father, everyone comes before you AND THIS IS A GOOD THING. God placed you in this position because you are capable. Serve your family. Fill your cup through service. Pour into your wife and children. Being a father isn't easy and it isn't supposed to be. But it is the best dang thing we have in this world. God speed, brother. You've got this 🤝

Mine is 1.5 yrs old. So my feelings are probably still in the adjustment phase of being a parent But also can’t just toss him out in the yard and say have fun… Also, typically up at 4am doing stuff for myself. Have about 1.5 hours once he’s up to enjoy breakfast and go on a walk. Then work 9-5ish. And we have 2 hours until he goes to bed. That means 5 days out of the week my kid only gets around 3.5 hours of time with me and I want to make that count. I’m sure this will change as he gets older. I’m assuming most of the parents posting might also be newer parents…

I genuinely do not get why kids take up 100% of their parents’ time these days. My dad and mom raised us 9 kids and didn’t spend every waking moment with us. I raised 4 of my own and didn’t spend every waking moment with them. And yet every reply is telling this burned out dad that he is doing the right thing, or even to go harder. Super weird to me.