໊

@adrgrondin @LocallyAIApp can I add my own model on iOS?

@adrgrondin What do you think about turboquant

Google’s Gemma 4 E2B running on-device on iPhone 17 Pro Gemma 4 is built from the same research as Gemini 3, has image understanding capabilities and can reason if needed Running at ~40tk/s with MLX optimized for Apple Silicon

@simonecanciello Where do you get that app stats

you’re overthinking while skin apps are doing $200k/month. now you can build one, create ai influencers, and make money even if you’re introverted.

@bridgemindai What models can it run well?

Claude Code rate limited me so hard I bought a $5,000 NVIDIA DGX Spark. Arriving tomorrow. A personal AI supercomputer. Anthropic cut off OpenClaw users. Slashed Claude Opus 4.6 rate limits. Told $200/month Max plan customers to use less. Then gave us a credit as an apology. This is what happens when AI companies have too much power over your workflow. One update and your entire stack breaks. Local models are the only infrastructure no one can throttle. No rate limits. No 529 errors. No surprise policy changes. Tomorrow I'm testing the DGX Spark live on stream. Running local models through real vibe coding workflows. The goal is simple. Never depend on a single provider again.

@Doomerzoomer That’s a man

alarm set for 7am your dream at 6:59:

@DanBilzerian Joe is absolutely right. There’s nothing we can do about this stuff, no sense in becoming frantic and panicking about something we have no control over.

Joe Rogan is such a pussy, Theo isn’t crazy, he doesn’t need to chill out, he’s just not a scared bitch like you.

@Adordev_ @RealEmirHan Hush ai

@RealEmirHan Jenna bared her soul and admitted those feelings were real, only for John to shut it down like a cold machine. It is heartbreaking to see him dismiss her vulnerability as just acting. He really went and killed the magic for us.

Jenna Fischer said The Office felt so real, she felt in love with John Krasinski “Part of me was Pam, part of him was Jim, and those parts were genuinely in love” However John said: “I’m sure she was saying something nice about acting relationship”

@ZherkaOfficial trp.

Its so funny how men figured this out recently when I knew this at the age of 15 lmao

@FlorinPop17 @lassvestergaard @marclou Dumbass

Hey @marclou i wanna delete my trustmrr.com account. Cant find a button and support costs money lol.

@scooturd2 @bumbadum14 @fromdusktildawn cry some more little baby

@peoplesuck @bumbadum14 @fromdusktildawn You're a moron

アメリカ人に聞きたいんだけど、 アメリカの一人当たりGDPは日本の2.6倍もあるのに、 なんでそんなに生活が苦しい人が多いの？ 高所得の人がたくさんいるんだから、再分配を少し強化するだけで、貧しい人たちの生活はぐっと楽になると思うけど、なんで再分配を強化しないの？ ちなみに、再分配を強化するのは社会主義でも共産主義でもないよ。 それは修正資本主義。君たちの大好きな資本主義を、ほんのちょっと修正しただけのものだよ。

@bumbadum14 @fromdusktildawn The gov won’t pay shit bro what are you talking about

In America, if you're poor enough the government will pay you to eat at McDonalds 3 times a day 30 days a month until you are so fat that you have to go to the hospital. Then all your hospital bills will be covered by the state funded insurance, and if you don't have insurance then you can just go the emergency room

@lydiahallie Down with Anthropic

Thank you to everyone who spent time sending us feedback and reports. We've investigated and we're sorry this has been a bad experience. Here's what we found:

@kullyyyyyy @Fortnite @Fortnite fuck you guys for not having tung tung

@Fortnite WHERE IS TUNG TUNG AND BALLERINA 😡

@SamTheLucioFan ai slop is already all over games. its 2026 not 2022

People fail to realise that Fortnite sets the standard for a lot of games. If they normalise AI usage (even if the skin itself is crafted by humans, the original design was made by AI) it will signal to others devs that it's fine to implement AI-generated slop into their games

@ThomasStockma20 @UbermenschMind LOL

@UbermenschMind She's already taken bro.

Every man needs a beautiful mid french foid like her

@itsjustmarky @0xSero What is that

@0xSero I think these are the future for home inference for the 90%. 10k-20k tokens/sec Qwen 3.5 27B

The first company to make AI boxes, with specialised AI models trained to fit on that hardware will be the next Apple. Would you buy? Should I start a company doing this?

@ollama No TurboQuant support?

Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework. This change unlocks much faster performance to accelerate demanding work on macOS: - Personal assistants like OpenClaw - Coding agents like Claude Code, OpenCode, or Codex

@06vmp Rate

some of you lowkey have impressive usernames

@naw103 @VadimStrizheus This is a great idea if you want to waste thousands of dollars to use models - that are substantially less powerful than the current SOTA private models - via CLI or janky local clients that are a pain to sync to your mobile device/nearly impossible to use away from home.

@VadimStrizheus Take it back before you open it and get higher memory, min 64gb if you want to take advantage of that machine. If it’s too late try using lm studio with qwen and drop the context down to about 33k tokens. get apple care too as your gona fry it sooner rather than later.

I just got a MacBook Pro M5 Chip > 16” > 24GB > 1 TB of storage What’s the best local model to run on this thing?

@mrmikeMTL Can I have $1

If you could telepathically say something to all 8.2 billion people on earth, what would you say?