Crown 👑

@the_jimmy_jones x.com/i/chat/group_j…

@awdyzx @DataChaz Use the real one instead of this one

@DataChaz It isnt that smart. Ive played around with it and cant do basic knowledge / image analysis

DO YOURSELF A FAVOR: GO DOWNLOAD THIS NEW LOCAL MODEL AND KEEP IT IN STORAGE. Even if you don't have a massive GPU setup, having offline access to an intelligent model is a crucial insurance policy. Free API access won't necessarily last forever. Right now, the 12B-27B range is the absolute sweet spot, and Hugging Models just highlighted a perfect candidate to download today: → GEMMA 4 12B CODER on @huggingface 🤗 It packs Google’s latest architecture into a GGUF format optimized for consumer hardware. What it delivers locally: → Fast, private code completion without the cloud → Real-world debugging and reasoning capabilities → Smooth performance on 12GB+ VRAM or a standard CPU Don't wait until you need it. Grab the weights and keep them locally 👇

@Hassaansaeed22 @DataChaz If you're memory poor use the new QAT version of gemma4 12b it's much faster

@DataChaz 12B means I need about 8 to 16 gigs of VRAM correct?

@ddarius94 @DataChaz You might be able to run hermes with it.

@DataChaz What can I do with just 12B? Remove unused imports and format code?

@MichaelGannotti White Glove Small business AI Solutions and consulting.

Have a service around AI? Data? infrastructure? Security? Me know so I can get you listed. SMF Clearinghouse- The clearinghouse for all things AI

@mr_r0b0t Have you tested?

A new specialist subagent, purpose trained to efficiently search your repo, was just released by Microsoft! Say hello to FastContext 😍

@bradmillscan @shannholmberg @hey_madni Followed both!

I need to setup a workflow to analyze and build a wiki of @shannholmberg & @hey_madni's posts. They are both fire-hosing Hermes-gold right now. Crazy value.

@MichaelGannotti @NVIDIAAI The models bigger than that are not worth running anyway, you are sitting on a beast right there!

@ciruai @NVIDIAAI Thanks. Little different in that it has 128 gb ram and my AMD unit has 96 but it will be interesting to see

Just ordered! @NVIDIAAI DGX Spark. Can't wait to get my hands on it

@MichaelGannotti @mr_r0b0t I thought you had the same system? (hardware wise)

@mr_r0b0t Yup.... the clickbait posts showing $1,900 ... If it was that cheap Id have bought one today

What is all this nonsense I keep seeing about the AMD Strix Halo being $2000!?! Half the posts aren’t even showing the correct device? It isn’t $2000, it was announced at $3999. That’s the only price I’ve seen anywhere. I spec’d out a comparable Framework desktop for reference.

@mr_r0b0t slop influencers.

@sirius_devops @sudoingX Nah it's cheaper, but not 2k. $3~

@sudoingX Stop the lies the AMD box is the same price . These LLM generated grift posts should get people banned

nvidia vs amd two boxes on my desk, both 128gb of unified memory. one is the nvidia dgx spark ($4,699). the other is the amd strix halo ($1,999), amd at roughly half the price. i'm running the exact same models on both, from a 3b all the way up to a 397b, same quants, same llama.cpp, and i'm posting every single number. here is why it actually matters. if the amd box just keeps pace, that's a nice story. but if it matches or beats a box that costs twice as much, the entire calculus for buying local ai hardware changes overnight. i already have the first numbers and they made me sit up. holding them for the full breakdown. stay tuned anon. this matchup is going to shake some ground.

@DBirker78883 @sudoingX Absolutely. I hope his benchmarks do it any justice at all.

@sudoingX I feel like the Strix Halo is the sleeping giant of local ai.

@sudoingX its not fair to use same quants on both when there are quants optimized for each.

the rules, so it's fair: identical models, identical quants, same llama.cpp build, both boxes idle, every number posted whether it flatters amd or nvidia. full disclosure, both nvidia and amd plus framework sent these units for honest testing, no money on either side. that's the whole point, nobody's paying me to crown a winner, the silicon decides. 3b dense up to a 397b moe, the full range. first numbers dropping soon.

@SMNYC1 @arunninghacker blows my mind what even a 3GB model knows. Where does it keep it all? 😂

@ciruai @arunninghacker Yes! That is amazing compression right?

I ran OpenCode riding an uncensored Qwen3.6 running on a Mini-sized shiny silver box with an NVIDIA card in it for a couple of days, and I assure you: all this ethics/regulations/export control frontier AI drama will be over very, very soon

@SMNYC1 @arunninghacker Imagine power is out for extended period and you're the only house which basically still has the whole internet self contained within it!

@ciruai @arunninghacker I feel like there has to be a market for the people who buy the storage 10 year food kits. They could rebuild civilization after they come out the bunker with ai in a box. Its a neat thought

@SMNYC1 @arunninghacker Currently solar powered and running AI locally. Hypothetically if power and internet goes out I could still run AI at home

@ciruai @arunninghacker Its an amazing way to compress a ton of information. Like wow. Having it work durable and offline would be good for if the web ever blows up. Its always a dns issue lol

@GMMeyer @benrayfield @BLUECOW009 I have no illusions about someone's ability to just download a weight file. Specifics are going to matter. That's why I say we can't really war game it without the details.

@ciruai @benrayfield @BLUECOW009 have you ever worked at an enterprise tech company? i can 100% guarantee almost no one has access to the model itself in the way you’re suggesting and any access of this kind is logged

Kinda crazy we never had the weights for a sota model be leaked

I rely heavily on openai still at home, even though I have access to dozens of models running locally and have spent hundreds of hours preparing for local only use. A couple of times in the last month the internet went out for an extended period (someone crashed into a main hub and died 🥲). Had to test everything I had been working on and keep moving without it. Found some important gaps. It's a lot of fun though, to be honest.

@ciruai @arunninghacker Yeah. I'm from the before times when we had our own computers and no internet. Ownership is kinda retro and good sec ops.

GPU VMs are much more expensive than just using an API. It's going to cost you $1+ an hour. Adds up if it's always on. An API for chatting probably will only cost you $20 a month or less but at that point why are you not just using gpt anyway? The reason to go local is to be in control.

@ciruai @arunninghacker Cool! Curious why not just host a vm somewhere? With a gpu

@GMMeyer @benrayfield @BLUECOW009 Would need to dig into specifics to map out the best way. Kind of hard to say hypothetically. Impossible to stop if people can't be trusted. In the end it's your people who protect you.

@ciruai @benrayfield @BLUECOW009 x.com/gmmeyer/status…