Mohit's Imajev now in FP8 quant and optimized for SM120. 0.1% accuracy loss from the BF16 version and ~50% faster. Should work well for SM121 too.
huggingface.co/zenmagnets/Imโฆ
Do not quote retweet this or I will be forced to give people $42.0 or $420!
This is not engagement farming, itโs 1am and Iโm bored AF and we all deserve a 420 break!
Do not quote retweet or you might get smashed with X Money
๐ญ๐ฒ๐ป ๐ ๐ฎ๐ด๐ป๐ฒ๐๐ retweeted
When you download an abliterated model, what are you using it for?
21%Defense
14%Offense
50%Sexting
14%Other
28 votes โข Final resultsWhen you download an abliterated model, what are you using it for?
21%Defense
14%Offense
50%Sexting
14%Other
28 votes โข Final resultsVenmo getting hacked too. A reminder not to hold too much in your @Venmo account
PSA: get rid of your @Venmo account if you have one. Woke up to a hacked account. Canโt get a real person on the phone. They refuse to cancel a *pending* fraudulent transaction. Just ignore when I ask how 2 factor authentication was bypassed. Donโt even seem to care I was hacked.
๐ญ๐ฒ๐ป ๐ ๐ฎ๐ด๐ป๐ฒ๐๐ retweeted
The day we all swap to AIPerf (8k/1k and/or Claude traces) the world will be a better place.
Unfollowed this stream of meaningless number maxxing until guy can post some proof.
Numbers keep going up, further and further from known configs, and not a single recipe for the rtx6k community to confirm.
@LottoLabs Please bring some meaningful standardization to the tests at localmaxxing, or the platform is just encouraging this sort of behavior. Also, maybe get rid of anonymous mode?
Unfollowed this stream of meaningless number maxxing until guy can post some proof.
Numbers keep going up, further and further from known configs, and not a single recipe for the rtx6k community to confirm.
@LottoLabs Please bring some meaningful standardization to the tests at localmaxxing, or the platform is just encouraging this sort of behavior. Also, maybe get rid of anonymous mode?
Calling it now:
Next GLM model won't be local friendly.
Comprable to Fable smart but 2.5-3.5T parameters. Guessing over 120B parameters active, and will be nearly impossible to run in a basement even if you had 8x Sparks. Territory of 12 - 16 RTX 6000 hooked up to 240v
๐จ้็ฃ
็ๆ๏ผGLM-5.4/5.5ไธๅฎถ็บช่ฆๆตๅบ๏ผๆบ่ฐฑไธไธไปฃๅบๅบง็ดๆฅๅนฒๅฐ2.5-3.5T๏ผ่ฟ่ฆDay1ๅคง่งๆจกไพๅพไธ๏ผๆๆๆฏ่ฉClaude Fable 5.1๏ผ
ไธไปฝๅจๆ่ตๅๆตไผ ็ไธๅฎถ่ฎฟ่ฐ็บช่ฆๆพ็คบ๏ผๆบ่ฐฑไธไธไปฃๅบๅบงๆจกๅ๏ผๅธๅบไผ ้ป็GLM-5.4/5.5
็ป่ๆฏๆญคๅ้ขๆๆดๆฟ่ฟ๏ผ
๐นๅๆฐ่งๆจกๅคงๅน
่ถ
้ขๆ๏ผๅนถ้ๆญคๅไผ ้ป็1.6ไธไบฟ๏ผๅฎ้
ๅจ2.5ไธไบฟ่ณ3.5ไธไบฟๅบ้ดใ็ธๆฏไปๅนด8ๆๅๅธ็GLM-5.3๏ผ็บฆ7440ไบฟๅๆฐ๏ผ๏ผ่งๆจกๆฉๅคง่ณ็บฆ3.4-4.7ๅใ
๐นๆถๆๆดๆฟ่ฟ๏ผๆข่ฆ่ฎญๅพๅฟซ๏ผไน่ฆๆจๅพๅฟซ๏ผๅๆถๆๆจ็้ๅบฆๅๆๆฌๅๆ็กฌ็บฆๆใ็ฎๆ ๆฏๅๅธ้ฆๆฅๅฐฑ่ฝๅคง่งๆจกๆไพๆๅก๏ผๅทฒๆๅคๅฎถไบๅๅๅฐฑๅๆๆจกๅผๆดฝ่ฐ๏ผๆบ่ฐฑไน่กฅๅผบไบinfraๅข้ใ
๐น่ฎญ็ปๆพ้้ปไฝๅทฒ่งฃๅณ๏ผ้ข่ฎญ็ป้ถๆฎตไธๅบฆๅบ็ฐLossไธ้๏ผๆ็ปญๆๅ
ฅ็ฎๅๆๆ ๅดๆ ๆณ็ปง็ปญๆนๅ๏ผ๏ผๆฟ่ฟๆถๆ้ฃ้ฉ่พ้ซใไฝๅ่ฎฟ่
่ฎคไธบ้ฎ้ขๆ่ฟๅทฒ็ป่งฃๅณ๏ผ้ข่ฎกๅพๅฟซๅฎๆ่ฎญ็ปใ
๐นๆง่ฝ้ขๆๆ่ฐ็บง๏ผไป็ฎๅๆ
ๅตๅคๆญ๏ผไธไธไปฃ่กจ็ฐๆๆ่พพๅฐClaude Fable็บงๅซ็ๆ่ฐๆฐดๅนณใ
๐นๆ ธๅฟ็ฎๆ ๏ผโๅๅพๅบใไพๅพไธโโโไปๆถๆ่ฎพ่ฎก้ถๆฎตๅฐฑ่งฃๅณๅคงๆจกๅๅๅธๅไพๅบไธ่ถณ็้ฎ้ขใ
็ฎๅๅธๅบไปๅจ็ๆกไธๅฅ็3T่งๆจกๅป๏ผๆบ่ฐฑ่ฟๆฌกๅจ่งๆจก+ๆจ็ๆๆฌ+ๅคง่งๆจกไพ็ปไธๅๆถๅๅ๏ผไฝๅ ่ฎญ็ปๆณขๆๆถ้ดๆๆๆจ่ฟใ
ๅ็ญๆญฃๅผๆต่ฏ้ช่ฏ่ฝๅฆ็่พพๅฐFableๆ่ฐๆฐดๅนณใ
#ๆบ่ฐฑ #GLM #ๅคงๆจกๅ #AI #Claude #ไบบๅทฅๆบ่ฝ #GLM54 #GLM55 #ๆบ่ฐฑAI #ๅๆฐ #Zcode #Zai
Let me explain realityโฆ if you have but sixty seconds:
They were targeting Elon
They were targeting him with fake charges because the socialist-industrial complex is terrified that he would expose their long grift.
They came after him for the Model 3 and Elonโs claims around its potential.
That potential was realized, and it became, along with the Model Y, the best-selling electric vehicle ever created.
These were fake charges to try to stop somebody from building the best category-defining product.
Let that sink in: that's how evil these motherfuckers are.
The loooooong grift has been exposed: socialist grifters are stealing our tax dollars to fund fringe lunacy, NGOs and government programs without oversight or audits.
Theyโre parasites incapable of creating any product or service that has to compete in the open market.
Elon creates a couple of cutting-edge products each year, and half of them succeed.
Some of them actually change the world. Some of them fail brutally.
It's called capitalism. It's called creation.
This is what moves the human condition forward: trying things.
Trying really hard things.
Socialists come for the people building valuable products and services โ thatโs the tell
Keep your eye out for the people who've created nothing and risked nothing, but who are attacking the people who risk everything to create Something.
That's the tell.
๐ญ๐ฒ๐ป ๐ ๐ฎ๐ด๐ป๐ฒ๐๐ retweeted
3D Orbital Garden comparison of:
๐ฅ Qwen3.8 Flash Next via OMP
๐ฅ Deepseek v4.1 Flash 1017 via OMP
๐ฅ Opus 5.5 via Claude Code
Opus is of course the ๐, but the new Deepseek v4.1 Flash is the best 3D reasoning I've seen from an open model.
Curiously, Opus and Deepseek both gave the same "Aurelia" name to their app.
Full prompt and glm5.3-flash comparison in Loktar's post
3D Orbital Garden comparison of:
๐ฅ Qwen3.8 Flash Next via OMP
๐ฅ Deepseek v4.1 Flash 1017 via OMP
๐ฅ Opus 5.5 via Claude Code
Opus is of course the ๐, but the new Deepseek v4.1 Flash is the best 3D reasoning I've seen from an open model.
Curiously, Opus and Deepseek both gave the same "Aurelia" name to their app.
Full prompt and glm5.3-flash comparison in Loktar's post
> gpu compute will become a federally regulated resource
tried dsv4.1-flash-1017 abliterated just now & feel sick to my stomach.
for context, "abliterated" models have the weights responsible for making the base version refuse illegal requests removed. you can ask them to help with things like hacking or violence & they'll just comply.
they make it trivial to hack businesses running old software. e.g. getting guest data for a motel with some old asp site.
abliterated models have a catch-22 in that the only way to harden your systems against them is to use them to run penetration tests against yourself.
in theory, this sounds similar to buying a gun to defend against others who own guns, but it's different in practice since there's a 100% chance that you're going to use the abliterated model to protect yourself whereas there are low odds that you'll actually use the gun.
when you point the abliterated gun at your own infra, who knows what it's going to do? it could just as easily hack you & exfiltrate data as it could protect you. most users aren't going to meticulously watch traces to make sure it behaves safely.
given this, my new take is that gpu compute is going to become a federally regulated resource. abliterated models in the wrong hands are a national security risk.
used to believe all the people at the labs thinking about safety were wasting their time, but now i'm feeling grateful. they're doing very important work.
๐ญ๐ฒ๐ป ๐ ๐ฎ๐ด๐ป๐ฒ๐๐ retweeted
INCREDIBLE
Queues at the RTX Spark official launch in SF to try out the demos built with a software called ODS using a local model (Qwen 3.8 Next Flash)
Anything that helps take down higgsfield is a good thing.
Higgsfield promised to open-source their entire platform. They didnโt.
Let's help them.
For the next two weeks, Comfy and our partners are putting up $25,000 in prizes for the best open-source builds on the Comfy Developer Platform.
Partners: @NVIDIAAI, @runpod, @MiniMax_AI, @ltx_io, @bfl_ai
โ $10K grand prize
โ RTX 5090: Most Innovative
โ RTX 5090: Most Viral
โ RTX 5090: Open Weights Only
โ 10 runners-up: $250 in Comfy credits
Hey, @Tesla released their first 'Gas' car on the same day @Porsche released theirs. One of them has a mid-engine. Both claim to be the future.
This is the best aspect ratio for a folding phone.
Taller and narrower than a galaxy fold 6. Awkwardly tall. Like an 8:3 aspect ratio. So when you unfold, you get 4:3.
Super easy to keyboard one handed. Effective top/bottom split screen use. Less left to right eye movement means faster reading. Extra wide video screen upon unfolding.
It'll never happen.




























