Sudo su
8.4K posts
Sudo su
@sudoingX
GPU/local LLM. more RAM and OSS... everywhere
Bangkok, Thailand Katılım Ağustos 2022
967 Takip Edilen29K Takipçiler
日本からこんにちは🇯🇵👋
タイランド人に質問があります🇹🇭🤭
タイランドでは、人の頭に触ると怒られるって本当ですか？😳
日本語
Sudo su retweetledi
@LeanKinPrazli @sudoingX Yeah the "you need a frontier model for agentic stuff" take doesn't survive a week of actually running it local.
English
First ever in-person My First Dollar pod ✅
He vibe coded an app in 2 days, posted 2 Reels, and made $45K. He showed me exactly how.
Episode out Friday 3pm EST.
English
if my agent can't use your product, you just lost a customer.
before i even click your link, my agent has already gone through it. if there's no cli, no api, no way for an agent to interact with what you built i'm gone. and so is everyone else who works this way.
the age of acceleration demands a new layer. your product doesn't just need a UI for humans anymore. it needs a protocol for agents. cli. api. mcp. something. anything my agent can talk to.
if you're still building products that only humans can click through, you're building for the last era.
the next wave of customers won't visit your website. their agents will. and if your product can't answer, you don't exist.
English
Sudo su retweetledi
hey anon, let me tell you this again because you only listen when repeated. qwen 3.6 27b dense q4 is the top king on a single gpu in the 24gb tier. if you own a 3090, 4090, or 5090 mobile, leave your work to this beast.
Sudo su@sudoingX
i declare qwen 3.6 27b dense q4 the king of a single rtx 3090 card. not even close. this model is absolute beast on local ai, ruthless on agentic loops, owns its own thinking. anyone can use it on single 3090, the weights are open, the stack is reproducible, the prompt is canonical, every claim below is verifiable on your own hardware. the octopus invaders one shot you are seeing is the visible test. i run these models on workloads you wouldn't think to ask for and i couldn't show you if i wanted to, and qwen 3.6 27b dense q4 quietly does the heavy lifting on a single consumer card while the rest of the field is busy explaining why it cannot. if you think a different model is king on a single 3090 right now, name it. drop your card, drop your model, drop your numbers. the throne is not crowded.
English
Sudo su retweetledi
let me say this out loud here: there is absolutely zero reason to use openclaw in may 2026. a general agent exists. hermes agent does coding, video editing, marketing design, research, browser automation, terminal work. one tool, all under your roof.
Joel - coffee/acc@JoelDeTeves
@sudoingX What is the reason for using Openclaw at this point? I have had zero issues with Hermes.
English
Agent view is the best Claude Code native way to manage multiple sessions, kind of like tmux built for CC.
We spent a lot of time getting the details right, I hope you enjoy it.
Claude@claudeai
New in Claude Code: agent view. One list of all your sessions, available today as a research preview.
English
will be a year building this in august. i get comments like "why not let ai finish it in a week." trust me anon i know. i use ai every day.
but i'm not building a vibe coded dashboard someone ships in an evening and forgets.
i'm solving a real problem i see every day in the market. something useful for everyone from a 12 year old to an 85 year old builder who just wants things to work. it doesn't exist well yet. that's why i'm building it.
almost a year. all alone. days and nights. and i'm closer now than i've ever been. just be patient a little longer. i'm dropping something useful for all of us.
Sudo su@sudoingX
i want to launch as badly as you want to see it. but there's a version of me that comes out in flow that demands robustness and reliability. and i'm not going against it. i don't ship half finished. it's just not me. there's a thrill in building something you know the market will appreciate. and you know because you are the market. if you're not your platform's first user, you probably won't make it. my hands aren't doing 10 things hoping one works. my hands, my mind, and my awareness are dedicated to one thing. and it's closer than yesterday.
English
i want to launch as badly as you want to see it.
but there's a version of me that comes out in flow that demands robustness and reliability. and i'm not going against it. i don't ship half finished. it's just not me.
there's a thrill in building something you know the market will appreciate. and you know because you are the market. if you're not your platform's first user, you probably won't make it.
my hands aren't doing 10 things hoping one works. my hands, my mind, and my awareness are dedicated to one thing. and it's closer than yesterday.
English
@sudoingX I got 2x 3090, still experimenting with models (moving to Gemma 4 31b Q8 soon)
English
buy a gpu. 3090, 4090, dgx spark, whatever fits your budget. tier doesn't matter. running your first local model does. the moment your first prompt lands with no api between you and the model, your brain rewires. that single moment is worth more than every take you'll ever read on a timeline.
English