Granite 4.1: IBM's 8B Model Matching 32B MoE • Hacker News Board

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#101

Post by alienbaby » Thu, Apr 30, 2026, 1:41 PM UTC

ramon156 wrote: post #12

cbg0 wrote: post #10

Earlier quoted context omitted.

So are we saying it's fine that the article is written by an LLM as long as it doesn't have the tell-tale signs of LLMs?

It's more about curating the things you're publishing. Why would I bother reading what you couldn't bother to read?

They could easily have read it, and thought , that communicates the information that it needs to.

No point creating busywork for yourself just shuffling words around when the information is there, no?

I guess it depends on what you want out of the article. Substance, or style?

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#102

Post by jasonlotito » Thu, Apr 30, 2026, 1:41 PM UTC

robotmaxtron wrote: post #61

"open source" show me.

Apache 2.0 License. Did you not click the link to the project? They even list it in the article.

> Apache 2.0 across the board, so commercial use is clean.

Did you just stop when you saw open source and come post this here because you couldn't be bothered to... look at the project and see it's cleanly and clearly listed.

Edit: Like. I get it. It's fine to question open source. But this isn't hidden. It's repeated and made clear multiple times. They even link to the license: https://www.apache.org/licenses/LICENSE-2.0

It wasn't hidden, it wasn't in some weird, out-of-the-way place. In fact, I found it so easily that I genuinely questioned whether it was real because of your comment. Like, why would anyone post what you posted if it was this easy to find?

NOPE! It was right there.

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#103

Post by mkovach » Thu, Apr 30, 2026, 1:47 PM UTC

geraneum wrote: post #96

0xbadcafebee wrote: post #82

People complain a lot about LLM-written articles, but the human comments here on HN are far worse. Mostly a bunch of people extremely proud of themselves for not reading an LLM-written article, and then a bunch of people who take it at face value and make the model seem almost useful, and one comment that actually looked at other benchmarks. Good 'ol humanity, good at.. being emotional... and not doing analysis.....…

> the human comments here on HN are far worse I already assume some comments here are LLM written.

I just wait until I'm hallucinating, then I comment. Keeps the classifiers honest.

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#104

Post by fwip » Thu, Apr 30, 2026, 1:56 PM UTC

cyanydeez wrote: post #100

wewewedxfgdf wrote: post #36

Earlier quoted context omitted.

I think LLM's have that sort of "summarise, wrap it in a bow tie, give a little dramatic punch as a preview to the next few points".

Guys, LLMs are build on all these social cues which were developed pre-model. There's atleast 10 years of pre-llm gibberish. This is to say: Marketers and spammers repeat the same things over and over, and these models are build on coalescing repetition into the basis. So yeah, of course people talked like this before, but it was always in some known context like linked in or a spam website.

Sure, but RLHF ended up emphasizing this to a level beyond normal human writing.

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#105

Post by woadwarrior01 » Thu, Apr 30, 2026, 1:59 PM UTC

The most salient thing about these models is that they're non-reasoning models. This makes then very token efficient and particularly well suited for local inference where decoding is usually slower than with datacenter GPUs.

Link to HF collection: https://huggingface.co/collections/ibm-granite/granite-41-la...

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#106

Post by sureMan6 » Thu, Apr 30, 2026, 1:59 PM UTC

0xbadcafebee wrote: post #82

People complain a lot about LLM-written articles, but the human comments here on HN are far worse. Mostly a bunch of people extremely proud of themselves for not reading an LLM-written article, and then a bunch of people who take it at face value and make the model seem almost useful, and one comment that actually looked at other benchmarks. Good 'ol humanity, good at.. being emotional... and not doing analysis.....…

The pro LLM rant is weird, LLMs "hallucinate" in creating detailed elaborate lies, the frontier models still do this egregiously, an LLM written article by default has 0 value since every single line could be true or it could be a convincingly crafted lie, every line has to be fact checked

I'm using Gemini 3.1 pro to help me research my thesis, it still with search enabled and on pro mode, invents entire papers that don't exist, and lies about the contents of existing papers to relate them to the context or to appease me, if I submitted an LLM written article based on the results its given me 80% of the article would be lies

Commenting to complain that the article is LLM written is helpful too since some people aren't able to distinguish

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#107

Post by whalesalad » Thu, Apr 30, 2026, 2:10 PM UTC

0xbadcafebee wrote: post #82

People complain a lot about LLM-written articles, but the human comments here on HN are far worse. Mostly a bunch of people extremely proud of themselves for not reading an LLM-written article, and then a bunch of people who take it at face value and make the model seem almost useful, and one comment that actually looked at other benchmarks. Good 'ol humanity, good at.. being emotional... and not doing analysis.....…

The thing is it's just a bunch of other original content that has been chewed up and regurgitated into something "new". Just show us the original content instead. This is by definition, slop. https://huggingface.co/blog/ibm-granite/granite-4-1

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#108

Post by aitchnyu » Thu, Apr 30, 2026, 2:13 PM UTC

zozbot234 wrote: post #25

agunapal wrote: post #18

If you really think about why MoE came into existence, its to save significant cost during training, I don't think there was any concrete evidence of performance gains for comparable MoE vs dense models. Over the years, I believe all the new techniques being employed in post training have made the models better.

MoE models will have far more world knowledge than dense models with the same amount of active parameters. MoE is a no-brainer if your inference setup is ultimately limited by compute or memory throughput - not total memory footprint - or alternately if it has fast, high-bandwidth access to lower-tier storage to fetch cold model weights from on demand.

Tangential. I'm a newb, can you name the concept of partitioning weights so we dont need to load whole thing?

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#109

Post by halJordan » Thu, Apr 30, 2026, 2:14 PM UTC

sureMan6 wrote: post #106

0xbadcafebee wrote: post #82

People complain a lot about LLM-written articles, but the human comments here on HN are far worse. Mostly a bunch of people extremely proud of themselves for not reading an LLM-written article, and then a bunch of people who take it at face value and make the model seem almost useful, and one comment that actually looked at other benchmarks. Good 'ol humanity, good at.. being emotional... and not doing analysis.....…

The pro LLM rant is weird, LLMs "hallucinate" in creating detailed elaborate lies, the frontier models still do this egregiously, an LLM written article by default has 0 value since every single line could be true or it could be a convincingly crafted lie, every line has to be fact checked I'm using Gemini 3.1 pro to help me research my thesis, it still with search enabled and on pro mode, invents entire papers that…

No, you're being weird (why are you calling people weird anyway, not helpful).

You're complaining about facts that have been true since words have been written on paper. If you read the article with the same criticality you read any other article you wont have the problem you complain about.

The reality is, you're only complaining because you hate ai. Cool, but dont dress it up and resort to name calling to browbeat the other guy

Re: Granite 4.1: IBM's 8B Model Matching 32B MoE

#110

Post by encrux » Thu, Apr 30, 2026, 2:16 PM UTC

phkahler wrote: post #92

0xbadcafebee wrote: post #82

People complain a lot about LLM-written articles, but the human comments here on HN are far worse. Mostly a bunch of people extremely proud of themselves for not reading an LLM-written article, and then a bunch of people who take it at face value and make the model seem almost useful, and one comment that actually looked at other benchmarks. Good 'ol humanity, good at.. being emotional... and not doing analysis.....…

>> The only benchmark it does well at compared to other models is non-hallucination and instruction following. I think instruction following is going to be the most useful thing these models do. Add a voice interface and access to a bunch of simple, straight-forward devices or APIs and you have a mildly useful assistant. If that can be done in 8B parameters it will soon run on edge devices. That's solid usefulness.

Anything that beats alexa-level intelligence on an edge-device is what I'd call useful as well, which shouldn't be too hard.

It's mind-boggling how bad current voice assistants sometimes are when you prompt them some fairly easy questions.