Damn, I hope this is not goodbye to uncensored models 😢
The core llama.cpp maintainers also work at HF and will now work for Nvidia I guess. Llama.cpp is a pretty significant part of the local LLM stack, especially since other tools like Ollama and LMStudio are just GUIs built on top.
Local LLMs have gotten to the point where they are a serious threat to Anthropic and OpenAI, and Nvidia has a lot of skin in the game. If Nvidia wanted to do some serious damage to local LLMs, they are now in a position to do so.
I’m also imagining they may try to squeeze out support for other GPU vendors. I’m using an AMD 7900 XTX to run Qwen 3.8 27B that I downloaded from HF to run on llama.cpp, which currently works like a dream. The 7900 XTX is the only sanely priced 24GB GPU left in 2026 (under $1k vs. $2k, $3k, $4k for Nvidia 24-32GB cards). Combined with OpenCode or Pi, a setup like this basically eliminates the need to use Anthropic or OpenAI products in the same way Jellyfin eliminates the need to use streaming services.
I’m sure Nvidia and their buddies don’t like one thing I’ve said in this comment and may very well be plotting to put a stop to it, so the community may need to step up our game and get our eggs out of the big tech basket.
Well the good news is they can’t take away from you what you already have. It being an open source project, I’m assuming if they do anything to deliberately gut AMD performance, it’ll get forked.
Also
The 7900 XTX is the only sanely priced 24GB GPU left in 2026 (under $1k vs. $2k, $3k, $4k for Nvidia 24-32GB cards).
Not on sale anymore, at least not at any vendor in my country, I searched an aggregate pricing website. Amazon has a few used ones left of some models, but that’s probably a 2 or 3 digit figure across SKUs. Hold on to yours with an iron grip.
What kind of tok/s are you getting with it on Qwen 3.8 27B and how’s the output quality? I may consider getting one if I can find one used or import from abroad.
Agreed, I was referring more to future updates. Obviously we’re good with what is available now.
I can’t speak to pricing and availability outside the U.S., but it looks like the one I got went up $100:
https://www.newegg.com/asrock-radeon-rx7900xtx-24g-radeon-rx-7900-xtx-24gb-graphics-card-triple-fans/p/N82E16814930084.
I traded in my 3070 and my final price was in the 700s. Last I looked, used ones were going for $800 on eBay vs. $1200 for a used 3090.
I run 3.8 27B at q4 with q4 context up to 200k. Decode is generally in the 30s and pp starts in the 700s and drops to the 400s as context approaches 200k. I use mostly Sonnet 5 at work and I would rate this setup with the OpenCode desktop app as pretty comparable overall for coding at least. Let’s just say I have no reason to use any cloud models, not that I would do that voluntarily outside of being compelled to at work.
I got mine used, around 600 imperial credits. Look for ads that provide proof of working and benchmarks (like FurMark)
I get around 40 token/s and it frequently has become reliable enough to drop sonnet for me. So take that as you will
Intel B50 and B60 pros are at microcenter right now perfect for this.
The core llama.cpp maintainers also work at HF and will now work for Nvidia I guess. Llama.cpp is a pretty significant part of the local LLM stack, especially since other tools like Ollama and LMStudio are just GUIs built on top.
I guess that explains why features like quantized KV caches are lagging behind. Maintainers are purposely dragging their feet.
the community may need to step up our game and get our eggs out of the big tech basket.
The community has chosen to not fight at all, which is worse. Anti-AI sentiment is at an all-time high.
Publicly. Privately, these hypocrites still whisper in ChatGPT’s ear when they get lazy enough. Or use some feature in Photoshop or some other software that they didn’t even understand was AI-driven.
deleted by creator
what if the LLAMA.CPP devs working at Nvidia improves CUDA support and keeps other vendor support.
It would be great but they seem to favour server computing as that has the greatest margins. I have a feeling being the biggest company on the planet at $5tn is not enough.
Oh no! -forks code- anyway…
do we have experts to work on it full time, paid?
Ok, how come these public utility databases are owned to be sold like that eg gitgub, twitter without any regulator pushback? Oh yea…
So they are just slapping random price tags on things now. It’s a database of AI questions. They have paid 13 billion dollars for a database, and everyone’s acting like that’s a perfectly rational sensible thing to do. No one in the financial industry has any sense anymore.
A company that’s only product is something that people either don’t want or actively hate has paid an eye-watering amount of money for a database to train their product on, this training will have no effect whatsoever on whether people want it.
I have this nice bridge with lots of training examples if anybody’s interested, 100 trillion dollars please
for a database to train their product on
Isn’t hugging face a database of already trained models?
Partially. But they also host datasets.
Yeah I don’t understand these valuations at all. I wish I did so that I could get a billion dollars for a website that doesn’t particularly own anything.
Is this some attempt at poisoning AI?
not everyone has a hate boner for AI
It’s an expensive toy that might become a viable product in a decade that doesn’t mean it’s a valuable company today. Irresponsible spending like this is exactly what led to the dot com bubble.
its a useful tool for me doing research.
What kind of research do llms actually help with?
In my experience, if the answer can’t be found in the top google results, the AI simply makes shit up.
The fact that it lies is so irritating, if it at least admitted that it didn’t know the answer it would at least be a useful search engine. The fact that it makes stuff up though means I always have to scroll past the AI summary, that I didn’t ask for, in order to actually go to the website to check the results myself, because I can’t trust it.
The worst part is that mostly lies for things that aren’t immediately obvious, so you ask it “what is the color of the sun” and it appears to work just fine, but the moment you use it for any real research, it will just fabricate things wholecloth.
thats completely false when you only ask the llm a very basic question like “what color is the sun?” you need to talk to the model like its smarter than a google search engine. “what color is the sun? pull the data from scientific articles and other sites that study the sun”
if you google the first question, you will have list of different pages, where if you use AI to search on your query, it will model an answer from thoese sources, with said sources linked, similar to a Wikipedia page.
There are thousands of papers on the color of the sun, its trivial to google a paper, if you need an LLM to do this, that’s on you. But if you ask it valve clearances for an indonesian motorbike in english, it will make it up, even though the service manual is available in Indonesian. If you ask it how to synthesize a chemical that nobody bothers to write about because its uninteresting or impossible, it will straight up lie.
i think that learning to prompt AI is somthing people lack as a skill and then call it bad and a liar like its some intelligence when it isn’t
Yeah because it was impossible to Google things in the past. Every time anybody comes up with a use for AI it’s basically just automating something that isn’t even that hard for you to do. If you want to automate simple tasks that’s absolutely fine but it’s not the second coming as people keep insisting.
Come back to me when an AI can actually add value to something, when it can do something that is not just automating a simple task, but it’s capable of doing things that humans are not. I keep being told that we’re only a few years away from the technological singularity, so wake me up when we actually get there.
when it can do something that is not just automating a simple task, but it’s capable of doing things that humans are no
No, credit when credit’s due, LLMs have arrived (by themselves) or helped to arrive at some mathematical conclusions, didn’t they?
A few of Erdős, some others.
Yes, it’s, a very small subset (duh), out of god knows how many they tried, and achieving the solution is made via technique called “infinite monkeys typing out Hamlet”, but credit when credit’s due (unlike LLMs that don’t properly attribute parts of the proofs).
Yeah I knew you’d say something like that. Mean while the rest of the human race is busy getting on with existing and not worrying about hyper specific mathematical constructs that have no bearing on actual reality. Let me know when you come up with some kind of actual concrete used for the technology rather than some toy situation.
It saves immeasurable time. Your time may not be valuable, but mine is.
Yeah and another way to say that is my job is complicated enough they cannot be automated via lua script with ambition.
Rather than being an ass wipe why don’t you tell us what you are immensely important and easily automatable job is. And then I guess you can go find a new career, or something.
I’ve posted examples in the past, enema bag. No new career necessary. My current career, attained with an MSc in Machine Learning, is serving me just fine.
Fuck
Anybody got a good list of models we should download right now before they start disappearing?
They wont disappear. hugging face is two things. its a model repo and a compute provider. hugging face has paid plans to run models on their systems. nvidia will use this to run on their backend. this is how they plan to make money from hugging face. its in their best interest to keep the repo stuff as is.
ELI5 huggingface?
Its a big box of toys but replace the toys with downloadable AI models and the box is a website
Wow that was an actual ELI5, thanks!
ngl the first image on their website is pretty much all the explanation you need
I am a LLM, what is this?
hosts all the ai models and is the primary resource for downloading them for pretty much all kinds, like depthmaps, masking too, also llms, inage generators, etc.
I know huggingface. I don’t know of anything they sell, though.
Neither does github
I’ve worked at plenty of places with github enterprise subscriptions. They definitely sell things, you’re just not the consumer they care about.
seconded, they charge $21/month/seat if you’re using the pro features; that’s $50k a year even for a smallish team of 20, just to use their website. Once you get to a bigger company with 800 seats, that’s $1M over 5 years, for something that was mostly built on free OSS software to begin with.
Not to mention the biggest bait-and-switch in history that they pulled off on Github Copilot subscriptions, that I’m guessing a lot of big orgs won’t have cancelled yet. They really are laughing all the way to the bank.
20*21*12 is more than 50k?
github sold premium services.
then Microsoft bought it.
? Github can cost tons of money if you abuse runners
isn’t that just github?
The Spark isn’t a bad computer, and they haven’t completely gotten rid of local GPUs, so Nvidia does somewhat care about local llms, but power corrupts and this is just more of it.
Buys what?
Buys the ability to control open source model distribution.
Oh no.
The good news is that there’s nothing stopping us from starting a competitor. Nvidia probably wants to use it to push their graphics cards.
It was only a matter of time
Pick up as many uncensored models as you can store ASAP. Those will absolutely be the first to go.
Do you have a list?
I would be less concerned about it being the end of uncensored models than I would be Nvidia finding ways to make sure there are no free models hosted there that work well on anything but Nvidia hardware for the foreseeable future.
let the fuckening begin!
gets a face hugger
Please tell me this is a rumor
It’s basically a done deal
Fuck
Aye
