THE RULE THAT GIANT MODELS REQUIRE GIANT RAM IS OFFICIALLY DEAD
COLIBRI runs GLM-5.2, a 744B model, on a 25GB machine with no GPU.
Because the model only needs a fraction of its parameters at once, colibrì smartly holds the core in RAM and streams the rest from disk on the fly.
While disk speeds limit how fast it types, getting perfect responses from a massive model on a consumer rig is a stunning proof of concept!
★ 2.1k stars · Apache-2.0
100% free and open-source.
Repo in 🧵↓
@0xSero Hope you destill and fine-tune something that runs in a Rasp Pi, or just enjoy de local inference.
I didn't want to peak on anyone just make the point and remind that not everyone has at least a RTX3060, and the current local models aim to high in the consumers
@MatthewBerman@endingwithali Obviously you need to read the code if you are not working alone or in a performance critical architecture or just at work.
Do you read the emails that the AI writes for you?
@MatthewBerman Anthropic pulls Claude Fable 5 offline one day after redeployment following a successful jailbreak by security researcher Pliny · Digg https://t.co/CYTKE9K1NQ
I just made VibeCodeViewer public 🎉
The first version was created with Fable, then I kept going with GPT-5.5 to polish the experience and fix some visual glitches I was seeing.
https://t.co/R8jOD1wc71
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: https://t.co/bwn0sximKZ