Looks like we are seeing small but mighty model breakthroughs, outpacing the pure capital firepower of SOTA providers. I love rooting for the little guy, but is it too soon to call it? To play devils advocate, could it just be the benchmarks are not efficient enough to capture success of real developer workflows?
15 minutes ago [-]
bakies 2 hours ago [-]
I've just started using qwen3.6:35b a couple days ago running on my framework desktop and rather impressed. It runs really well and reminds me of probably the first Claude model I used. It's the first local model that's actually working for me in a coding agent I've tried. Very exciting!
diseasedyak 21 minutes ago [-]
I'm running qwen36.:35b:iq4 IQ4_XS quant. Takes 18 GB of RAM with 131k context window. Seems to be really good. Have it running local stuff via Hermes, using a cloud model via Ollama (Deepseek V4-Pro) for heavy lifting.
smcleod 1 hours ago [-]
Try 27b, it's significantly smarter than 35b-a3b (although it is slower, it's not so bad with MTP).
It feels sometimes like optimizations are only starting.
secretslol 10 hours ago [-]
Am I right in thinking this is a tiny model which has been trained well to reason, and that's it? Makes me think of a smart person who doesn't know anything about a given topic, but with the right tools will go and research the heck out of it. I really like the sound of this... why have models train on learning anything when you can just train them how to learn and let them get on with it from something as small as a Pi Zero and an internet connection.
numlock86 9 hours ago [-]
This has been my dream ever since. Instead of encoding "all the knowledge" into those parameters, how about just making a model that has the same size, but all (or rather most) it does is reasoning? Just give it the ability to browse the net (e.g. language specifications, documentation and best practices) and just have it do its thing. Why does my coding agent need to know the population of New York, know a cheese cake recipe or the general lifespan of an ostrich? Just give it the bare minimum knowledge to think and reason about, and let it figure out the rest.
Sadly that's not how LLMs work, since all they do is "token prediction". At least the models we have to today ...
dandaka 5 hours ago [-]
I think this is a well known concept, which we can't deliver yet. LLM/transformer give us reasoning engine as a byproduct of its design, but it is quite ineffective. If we can distill reasoning, if reasoning can be achieved without general knowledge, it will be a very effective machine.
Some amount of knowledge is required for reasoning. Maybe such model can dynamically knowledge domains to have taxonomy. For example, model can't effective reason about development task, if it has no knowledge about development best practices. But population of New York or recipies can definitely be loaded run time with tools.
sigmoid10 4 hours ago [-]
>Some amount of knowledge is required for reasoning.
This is the root of problem. If you think about STEM universities, they don't really teach you things you need in the real world. They teach you what you need to know in order to go out there and accumulate the necessary information which can then be used to solve problems. Giving a person access to the internet or a super powerful calculator (like Mathematica) won't mean that they can do anything useful. They need tons of experience to use these tools in an effective way. That experience is basically all that implicit adjacent knowledge that we pick up along the way getting our degrees. And LLMs pick that up during pre-training. Drop this part and the outcome will be worthless.
dandaka 34 minutes ago [-]
Take mathematics as an example. Humanity has found math notation, which allowed to express math rules — distill them to the core. Before math was expressed in prose — a very inefficient way, very similar to current LLMs.
In my school, math teacher was giving me prose, which I was converting to math notation. I could argue, that this prose→reasoning conversion is not required at training, and can be obtained at inference time with search tools.
XCSme 3 hours ago [-]
Yup, you still need knowledge. Even if you have access to all the data and tools, you still need to know what to search for, what tools to use and to understand what the user is asking.
Our computers can already do everything, have access to all the tools and information, yet they still need a human/intelligence to use it and apply to specific problems.
Even defining the problem requires knowledge.
As for the tools, if the model has access to 1000 tools, how would it know which one to use if it doesn't have any knowledge itself?
What if I ask for "table tennis spin" it had a "magnus effect calculator", how would it know to make the connection between the two?
dandaka 30 minutes ago [-]
Model can use tools to get that knowledge. In your example, read Wikipedia page about table tennis. Imagine a reasoning engine with a big enough context, that knows nothing. A path built from first principles to understand "table tennis spin" — does not look very long for me.
XCSme 18 minutes ago [-]
How would it know about Wikipedia and when to use it? From the tool description? If we had 100k such tools, then that wouldn't even fit in the context.
This is only one example, plus if the topic is more complex, maybe it had to search/learn everything (what is table tennis, what is spin, what is a human, what is a ball), etc. So it would be like spawning a baby human, have it spend an (instant) life learning about the world before providing an answer. Maybe this could work in 10 yesrs, if models get stronger with huge context lengths and almost instant data retrieval. Is it the best way to go about things though? Most animals have most of their core abilities embedded in their DNA and "instincts". A cat doesn't have to learn what a bird is in order to hunt it, it's already "embedded" in its neural pathways, or even deeper, at a full-body level. Those type of systems are a lot more efficient than the learned ones. Maybe the best future AI, will have everything already embedded, instead of just being a strong reasoning machine. All AI responses should be instant and like "reflexes" instead of reasoned steps.
athrowaway3z 7 hours ago [-]
This is me vibe-splaining something I don't know a lot about, but I doubt there is such a thing.
If "all the knowledge" is what our models now do, what exactly would be the most extreme "none of the knowledge +search" ?
> language specifications.
It would load in all the knowledge to figure it what "language" means, then it would continue trying to decode what "specifications" means.
That might sound absurd, but to figure out the population of New York It's either: Just going to google it, or derive from primary sources.
But how is it ever going to interpret the primary sources? It needs to understand the question, how complex a question is, and how complete an answer is and how things relate. Thats just _too_ much language.
There might be a way to compact this down into a LLM-native language such that the request of `the population of New York` or `use best practices` is encoded without our messy human language for a reasoning model to work with, but the encoding itself has to be done by the "all the knowledge" llm. Now it seems we just rebuild something related to MoE with extra step afaict.
3eb7988a1663 9 hours ago [-]
It would also reduce training costs to nothing. Current methodology requires continual retraining to scoop up new facts. If you can do a one time "this is how to think" - that could conceptually work forever, just plug in a new database layer that can be queried as required.
fjsoxjdnwk 4 hours ago [-]
But isn’t that what “training” is anyway? They train LLM today like that and the database becomes the parameters. You can post train on smaller corpus for purpose-built stuff.
tomaskafka 8 hours ago [-]
Education had this sad 15 year period where it thought “competences” are all you need.
Turns out that without the world knowledge to have a base of facts, it is not.
g8oz 15 minutes ago [-]
Competences were always supposed to be supported by demonstrable knowledge and skills and behavior.
So I don't think it's true that relevant knowledge was deprioritized. At least it wasn't supposed to be.
gmac 5 hours ago [-]
Basically: you can't teach people to think without giving them some facts and ideas to think with. It's like trying to teach woodworking without giving the students any wood.
brookst 2 hours ago [-]
“Theoretical tennis”
inopinatus 1 hours ago [-]
Any sufficiently general superintelligence will deduce the existence of rice pudding and income tax from Cartesian first principles.
2 hours ago [-]
dminik 7 hours ago [-]
I mean, this really doesn't sound useful even if LLMs worked that way.
First, if you know nothing you don't even know what you're missing or what to search for.
Then, without unlimited context, you have to do research for every task all over again every time.
regularfry 6 hours ago [-]
> First, if you know nothing you don't even know what you're missing or what to search for.
RAG on the initial prompt would be the first thing to try.
> Then, without unlimited context, you have to do research for every task all over again every time.
Thing is, we're really really good at building very fast search engines. Doing research all over again every time shouldn't be a problem.
vitro 5 hours ago [-]
Couldn't you build some internal knowledge that would stay and you could teach a model this way. A very fast local memory of some sort. You could also specialize model this way so it is very skilled in your domain. The more you use it, the smarter it gets. I guess the problem is for the model to decide whether the information stored in memory is sufficient or not.
regularfry 5 hours ago [-]
You could, but it's driving in the wrong direction to try to build that knowledge into the model weights because you'll always run into a capacity limit sooner with a small model than with a larger one. The thing the model is specialised for is linguistic understanding and the reasoning process itself, and you max that out at the expense of domain-specific knowledge. If you take "as few weights as possible" as a given, I think the interesting question is how small you can make the model with externalised memory. The openclaw and hermes people are all over this sort of memory problem: using the local filesystem or a local database of some sort is exactly a "very fast local memory" where the more you use it, the more knowledge it gathers. Whether that translates to it being "smarter" is a deeper question than it looks.
scotty79 6 hours ago [-]
The model they built knows a fair bit apparently. You can't get 94.3 on AIME26 knowing nothing.
LoganDark 4 hours ago [-]
Reasoning alone can’t always predict all the bits of knowledge you’d need to sufficiently solve a problem, that you would research when planning.
Lerc 8 hours ago [-]
I think you could probably train a model to consider boolean logic, modal logic, and mathematics reasonably well, but there is still a pretty big leap between that and thinking about things.
Even the most basic questions such as put a ball in a cup and place it on a table upside down then pick up the cup and put it in a box.
Requires knowledge of things not mentioned in the question (notably gravity).
Strict definition of all terms quickly gets you into a quagmire of complexity. Some base level of knowledge about things is required for you to give it instructions. If it only knows how to reason, it lacks any idea of what to aim to achieve.
There is quite a pronounced disconnect between the vast stores of written data that models are trained on and robust consideration of a topic. I do wonder if the path can be directed by the order of training.
For example if you train a model to basic literacy using tinystories, then math and philosopy texts, then psychology, and sociology texts, and then finally the mass data of everything from conversations and rants, to code and fiction.
Does that end up with a significantly different model to one that is trained on books on acting, creative writing, and fantasy novels, before introducing the same final mass data set.
How much does it's current ability allow it to contextualise new training data?
mejutoco 3 hours ago [-]
> Even the most basic questions such as put a ball in a cup and place it on a table upside down then pick up the cup and put it in a box.
I do not think this is a great example. First, it is not a question. Second, it seems very related to robotics. A model itself cannot put a ball anywhere, it can just call tools and answer in text, image, etc.
An LLM seeing "put a x in a y and place it on a z upside down then pick up the y and put it in a z2." and then a question about what happens could check a rag for properties of those x,y,z,z2 and still answer. Alternatively, this could be useful for coding, for example. And that is a very extreme example. Some basic language plus tool use could go quite far. I think it is a very interesting direction vs here is a gpu the price of a car.
grumbelbart2 38 minutes ago [-]
The thing is we tried that for decades, using more formal logic to build reasoning engines. And we never got it to be even a fraction as good and generic as learning-based LLMs are today.
mejutoco 33 minutes ago [-]
I dont think think my point is getting across. This is in the context of how much world knowledge a model needs to be trained on, not llm vs not llm.
kitd 5 hours ago [-]
"The right tools" in this case might presumably include, eg, a set of repos + docs and specs on the various technologies being used. Or a library of text/images and background docs on style and techniques use to create them.
That plus this model should give you a very powerful and focussed assistant.
3 hours ago [-]
soulofmischief 3 hours ago [-]
Choosing between a model that can only "reason" and a model that has extensive knowledge and "reasoning", the latter will be undeniably better. Advanced reasoning requires cross-domain knowledge, superb pattern recognition, which can only be gained through the same mechanisms which give you a knowledgeable model.
Except for the most basic of tasks, such as "turn on my lights" or "cross-reference these two lists", I wouldn't trust a small model to be as conscientious and reliable as one with deep knowledge.
altmanaltman 8 hours ago [-]
Yeah but don't you think like that's an oversimplication with the metaphor if we assume this model can do a smart human-level analysis and distillation of knowledge, no? I mean if that were true (i.e. its just like that) then yeah there is no need for massive models but I really would doubt that.
Even recent massive models do not work anything like a smart human does at the moment so why are we assuming this can?
deftio 10 hours ago [-]
There is some base level of intelligence any model needs to be useful, even in narrow tasks.
Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
Small models need to have enough base knowledge to be able to be good enough -- even in a seemingly narrow regime. Where is that? Obviously they don't need all the obscure knowledge of a frontier model but there is some base level which is probably more than it would first seem.
swiftcoder 8 hours ago [-]
> To drive a car requires being able to read
Emphatically, it does not. Passing your drivers test may require being able to read, but plenty of illiterate people around the world drive just fine.
There is a reason we made all the common road signs recognisable purely by shape/colour, after all.
avereveard 6 hours ago [-]
Until they reverse on a highway and kill a family. Being able to drive isn't where parent poster put the bar
swiftcoder 6 hours ago [-]
I don't see what reading has to do with knowing not to reverse on a highway. It's not like they put up big glowing signs that say "wrong way" like in a video game.
popopo73 5 hours ago [-]
In Australia, you will see signs on freeway offramps pointing to any cars attempting to drive on to the freeway 'WRONG WAY GO BACK' [0]
Though it is true you don't need to be able to read to operate a vehicle, you /do/ need to be able to read to operate a vehicle safely.
And for those who can read: could you teach someone how to drive using an LLM? Sure. Safely? Probably not.
Most of the world follows the Vienna Convention on Road Signs and Signals, where all the important road signs are understandable without reading. This is how no entry signs look around the world [1]
Especially important in places like Europe, where it's common for the driver to be able to read, but unable to speak the language of the country they are currently driving through. I can't speak any Polish, but can travel on Polish roads just fine
This. It’s bizarre to claim that it’s impossible to drive safely in a country where you don’t speak the language. I’ve driven plenty in remote parts of the Middle East despite not reading Arabic, and never once went into oncoming traffic.
mycall 2 hours ago [-]
I've had some close calls with roundabouts with one-way on/off roads, especially figuring out the bike lanes. None of it required reading but would have been safer for sure.
Then there is Hanoi.
coldtea 4 hours ago [-]
>Though it is true you don't need to be able to read to operate a vehicle, you /do/ need to be able to read to operate a vehicle safely.
Not really. You just need to be able to decipher the sign, which is trivial, even if you can't read it or spell it.
supergarfield 5 hours ago [-]
I agree that drivers should know not to reverse on a highway regardless of local signage.
But in situations that could be ambiguous, I think this is a regional difference - the US, Australia, part of the rest of the Americas use lots of text on road signs (including literal "wrong way" signs); Europe and much of the rest of the world use far less text (including purely pictographic "wrong way" signs). Especially important in Europe where drivers just can't learn 20+ languages.
4 hours ago [-]
avereveard 5 hours ago [-]
There literally are "no u turn" signage where you are supposed not to do that. They literally put up signs for it. It is not glowing in the sky, and it doesnt need to be, and doesnt help making a point strawmanning it.
swiftcoder 3 hours ago [-]
> There literally are "no u turn" signage where you are supposed not to do that
And it's trivial to learn "no u turn" and a few other basic signs as a graphic, even when you can't read them (or can't read in general).
It's also trivial to do a u turn even when you can read, know what the sign says, and you feel like doing one because no car is coming anyway, and millions of people do that everyday too.
coldtea 4 hours ago [-]
Not reversing on a highway doesn't require reading, just driving sense.
And whole lot of people have done stupid shit like that while perfectly able to read, many even with masters and PhDs.
delis-thumbs-7e 39 minutes ago [-]
> To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
It is really strange to see comments like this here, where people seem to reduce some basic human action into how it would work in a text-only computer game. Driving itself requires mainly muscular memory how to operate the car, which why people who drive a lot can just go on autopilot and think something completely different when driving long distances. That is of course a form of kno, but you only get it through repetition. Of course driving in traffic requires far more, basic understanding of traffic law etc, but most of driving is muscle memory, understanding the vehicle and anticipating future occurrences. Why we apes are so good at this is because we have some million years of evolution of just using our bodies and seeing what happens. And of course we all seen the gif of an orangutang driving a golf cart (how real it is I’m uncertain), so there’s that.
I think might help to think models not as some future replicants, but models with certain capabilities in certain domains. It probably doesn’t make much sense to ask Opus 4.8 to drive you around as it doesn’t make sense to except a small image model made for edge devices to be able to write a novel. Perhaps we should just think of them as tools with certain applications they are made for.
ygjb 9 hours ago [-]
> Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
I would be interested to see a formal study of this. I say this not out of anything other than a observation that I think the only real blockers are a) judgement, and b) physical reflexes/strength. As a kid I was certainly aware of ice,snow, and rain, because I road my bike year round and had low confidence in my own ability to control my bike on snowy or wet terrain, especially during season changes. That translated into learning to drive in northern Canada in the winter and applying those lessons to driving.
In an environment devoid of consequences, I have seen kids operate driving simulations (both real simulations, and video games) with a degree of precision that is shocking, including seeing several 9-11 year olds play the simulations and games with a much higher degree of confidence than adult drivers. Children have an awareness that the simulations are consequence free, unless given other motivation. Adults that are consistent drivers have muscle memory and preconceived expectations that govern the decisions they make when playing the game. I am curious about the level of training and exposure required for children to overcome their lack of awareness of the hard limits and consequences of driving and driver error, versus the amount of training and exposure required for expert drivers that are novice gamers to stop applying their learned experience to consequence free simulations.
attila-lendvai 6 hours ago [-]
if you don't sit in the car you lack a lot of information. driving without them is almost a different skill.
(i'm above average in both)
threatripper 8 hours ago [-]
Ask people who grew up on a farm in a rural area. Sometimes you have to even if you can't and you do.
subscribed 6 hours ago [-]
I was driving a tractor since 12, including on the road with small farm equipment, and indeed, mostly out of the necessity, but I also received a lot of tuition (from licenced drivers) to know how to behave.
Different times though.
coldtea 4 hours ago [-]
Not that different. Still happens all the time all over the world (the west included).
madduci 6 hours ago [-]
True story, they can already drive a tractor at 10 and I know people who learned to drive a proper truck at 13 too
universa1 8 hours ago [-]
A 10 year old definitely,and 5year old is close, but not unrealistic, To drive a car you don't need to be able to read... To drive a car on the road with other people is a whole other story :-)
3eb7988a1663 8 hours ago [-]
I suspect plenty of five year olds can do a respectable job in Mario Kart, Gran Turismo, etc driving games. Gaming has too low of stakes to judge them on perfectly adhering to the rules of the road, but the ability is there.
And AI tried telling me that Uber for Dogs (dogs are the drivers) was a terrible idea…
coldtea 4 hours ago [-]
>To drive a car requires being able to read
Millions of people do drive who can't read. It's very common in parts of Asia, Africa, Latin America, etc, especially rural, but even in cities.
There are places where oral exams and audio-assisted testing is allowed. And there are places where people just drive (and drive fine) not bothering with a license.
smokel 9 hours ago [-]
Being able to drive a car properly also depends on having the right exploration-exploitation balance. A three-year-old is likely to explore too much in a situation where mistakes can be dangerous.
This requires not only knowledge, but also the control systems that develop with the prefrontal cortex. LLMs don't do much control yet.
satvikpendem 8 hours ago [-]
While I agree with your assessment, probably could've chosen a better example, as in many countries young kids even as young as 8 will learn how to drive.
embedding-shape 7 hours ago [-]
In some countries they even let kids as young as 16 drive, no wonder they have so many accidents.
swiftcoder 6 hours ago [-]
Several US states will give you a permit to drive a farm vehicle on public roads at 14. Illinois recently passed an amendment to allow farm kids to drive a semi-truck at 16. And there is absolutely no minimum age for driving so long as you are on private land - I have seen 8 year olds driving a pickup truck round a farm...
skeledrew 6 hours ago [-]
> To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball.
Conflation. That's to drive a car safely. To just drive a car one only need know to press gas to move, press brake to stop, turn steering wheel to change direction and maybe use a gear stick to shift into drive/park (car can be modified to abstract that away). Not much more complex than riding a bicycle; maybe even less since no need to learn to balance.
8 hours ago [-]
wilg 8 hours ago [-]
This is more of a question of the definition of "drive a car" than any specific issue about intelligence. Drive a car without errors? Impossible, and now we're into a subjective discussion about what feels intelligent. Pass the DMV test? Probably. How complicated are the conditions? There are plenty of drivers with bad judgement. It's a quicksand sort of discussion.
sorenjan 57 minutes ago [-]
How would you best utilize a model like this for coding? I take it it's not meant for vibe coding a full app, and the reasoning probably makes it unsuitable for autocomplete. Would you use it to implement specific functions? I looked at one of the coding benchmarks used, Live Code Bench, and it seems to be problem descriptions with sample input and output, and then a solution with a single function or class.
Seems like a really good model to use in an IDE when you still want control over the code structure then.
aswegs8 27 minutes ago [-]
Not sure if it's suited for that. If you read the article it's stated that it is basically a research project to see how far they can push it with small models.
gslepak 10 hours ago [-]
Note that these are Python-only results, the model will not do as well with other languages.
I'm glad to see more domain-focused SLMs, we need more of them! A programming focused MoE should work well across many languages.
rcarmo 4 hours ago [-]
If it writes functional Python instead of cosplaying as a Java programmer and cramming code with classes and accessors, it's already better than Opus...
nsingh2 9 hours ago [-]
Lots of confusion about what this model is actually focused on.
It is a cheap specialist for closed-world, verifiable reasoning tasks like math, self-contained coding problems, and similar.
"Closed-world" means the needed information is already in the context. It is not a tool-using agent that can discover missing context. "Verifiable" means answers are hard to generate but easy to check.
So no open ended research, repo wide agent work, factual Q&A, or SVG generation. More of a compact reasoning module for bounded problems.
nsingh2 8 hours ago [-]
To follow up on this, I had it solve a nasty ODE problem that I saw in the recent Mathematica 15 release post:
Solve the following first-order ODE for f(x):
((-1 - 2*x)*f(x)*tan(1 + x - exp(-61 - 2*x)*f(x)/x)
+ exp(61 + 2*x)*x*(1 - x*tan(1 + x - exp(-61 - 2*x)*f(x)/x))
+ x*tan(1 + x - exp(-61 - 2*x)*f(x)/x)*f'(x)) = 0
Find the general solution f(x).
And surprisingly it found a valid solution! Extra impressive because it runs 25 tok/s on my measly RTX 2070 super.
f(x) = x*exp(61 + 2*x)*(1 + x - arccos(C/x))
C is an arbitrary constant.
Apparently Mathematica 14.3 couldn't solve this ODE.
kanbankaren 1 hours ago [-]
Qwen 3.5 9B Q4_K_M solved this using 10K tokens in 5 mins on a RX 7600.
The answer is exactly what you have posted. I am impressed by Qwen!
le-mark 3 hours ago [-]
How do you know it’s a valid solution? Are you able to verify it yourself?
krageon 18 minutes ago [-]
This is a math problem with a math solution. You verify it with math
kame3d 7 hours ago [-]
Interesting!
I just tried the quantized Q4_K_M from [1] in my RTX 2070 Super, it ran at 110 tok/s with 1800 tok/s prefill, and found the same solution to your prompt. It generated valid LaTeX for the answer but its reasoning trace uses mostly compact ASCII math notation. Took 3min 22s to answer, spending 22k tokens almost all on thinking.
How do we know the solution isn't in the weights though?
skeledrew 6 hours ago [-]
If it can code well then once you put it in a loop with an interpreter it can do anything.
NotSuspicious 9 hours ago [-]
The interesting thing about models this small is they should be able to be put on a single Taalas chip (the HC1 already runs a Llama 3.1 8B model). We're already at the point where half-decent reasoning could be run on an ASIC (and at mind-boggling speeds).
pants2 8 hours ago [-]
Yeah, if they can fit an 8B model that's really good at improving the output by thinking, running at 16K tok/s on Taalas would be mind-blowing.
le-mark 3 hours ago [-]
Given this and the quality of open models, it makes no sense to me that there’s a future for Anthropic et all?
james_marks 2 hours ago [-]
Packaging a capability into a consumable form will still be business.
It's like web hosting; all the open source tools are there and free, and yet website tools, hosts, etc flourish.
WhiteDawn 1 hours ago [-]
It’s true, but hosting prices are still within spitting distance of rolling it yourself.
SOTA providers are expecting some level of margin. Companies everywhere have a tight eye on their AI bills right now.
The motivation is there if the models get good enough, even if it’s more painful.
iamgopal 51 minutes ago [-]
Two model, one is optimised for system, reasoning etc, second is optimised for specific language ( rust or go ? ) , both small enough to run on local computer, will it work ?
noperator 11 hours ago [-]
Having some success while testing this model out as a replacement for GPT-5 nano in source code security review. Running on RTX 3090 (24 GB VRAM) via vLLM. It's not great on structured output (as noted in the model card) but I'm working around that in my harness.
dummydummy1234 10 hours ago [-]
Can't you just force it to do structured output via constrained generation?
hypfer 8 hours ago [-]
> but I'm working around that in my harness.
How?
uberex 3 hours ago [-]
Maybe limiting logits to what is syntactically correct? E.g. {"hello" has to be followed by whitespace or colon. Any other logits get dropped.
virajk_31 2 hours ago [-]
SLM when trained for single use case often beats the LLM. That's both the advantage and limitation.
androiddrew 3 hours ago [-]
I have been thinking about how to use this. Since it doesn’t support tool calling I have been considering a dual model deployment, where a small tool calling llm drives the majority of the user experience, and vibe thinker is tapped for reasoning by the other llm.
So who has suggestions on small models with excellent tool calling capabilities?
smallerize 1 hours ago [-]
Gemma 4 E4B and Qwen 3 4B are pretty good, but fine-tuning makes them really good. There are tradeoffs at this size, so you'll have to find (or make) a finetune that does what you need.
j-bos 2 hours ago [-]
Maybe bonsai 8b would make the duo, if you do try it, pls post here as I'm a bit curious too.
reddec 3 hours ago [-]
granite 4
cold_harbor 48 minutes ago [-]
GRPO skips the value network that makes PPO expensive — it scores candidates relative to each other within a group. that's what makes verifiable-reward training practical at 3B scale
aero2146 11 hours ago [-]
I tried generating the classic pelican svg, but it failed horribly just showing me a rectangle and a black circle...
fwipsy 10 hours ago [-]
I think this is predicted? Part of the story is how they were able to preserve core reasoning ability while cutting knowledge like "pelicans have wings."
> these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios.
pylotlight 10 hours ago [-]
The only real essential item here is tool calling capability is it not? So I assume they tested a strong read/write/edit tool consistency?
nsingh2 10 hours ago [-]
This model doesn't support tool calling, was not part of its training. It's focused on Python (and I think C++) competitive programming and mathematics tasks, i.e. tasks with verifiable rewards. So if you have a task that fits that description, the size-to-capability ratio is good.
These kinds of models might be more useful as tools to be used by larger orchestrator models, than being the orchestrators themselves.
btown 10 hours ago [-]
I'm not seeing any mention of tools in the paper, much less a bias towards "curiosity" to use those tools when it encounters gaps in its knowledge. So perhaps this is a good proof-of-concept that single-pass code generation is viable with this small a model - but we're still a long way from a viable solution.
kristopolous 8 hours ago [-]
try it again but give a careful explanation of what a bicycle and a pelican is and how the pelican would sit atop the bicycle. Then give it a reference to the SVG tags you want it to use with documentation.
Imagine you want to make a smaller model that is really good at one thing, say, driving a car. You could remove the parameters that lead it to correctly answer, "What is the powerhouse of the cell?" or, "Who was the first president of the United States?"
It would look really dumb if someone asked it that, but that's fine. You're trying to make a model that is optimized for efficiency for a specific task. As much as possible, you should prune uncorrelated things.
pylotlight 10 hours ago [-]
SVG generation is a useless test, what's there more to know?
steve_adams_86 10 hours ago [-]
What if you're reasoning about how to generate SVG correctly?
Mtinie 10 hours ago [-]
In this case, I’d expect it should make a web search tool call to find the Python library best suited for SVG generation and manipulation, and then use what it learns there to execute the task you’ve asked it to do (either asking if you’d like to incorporate the library as a dependency or to roll its own implementation of a subset of the features if that was your preference),
Assuming tool calling hasn’t been entirely stripped out of this model.
As in, you learnt that a useless test that no one should be using was tested here, that's what you meant right?
fransje26 12 minutes ago [-]
right?
brainless 6 hours ago [-]
I recently came across this model and I would love to try it with my coding agent soon.
I really like the idea of small models that can reason but do not have too much knowledge. Also, no emphasis on tool calls. I think the agent should do the heavy lifting and reach half way.
I use really small models, like Qwen 3.5 0.8B to 9B - no tool calling, no MCP, no skills, nothing. No multi-turn chat even. Models are given very specific tasks using a vast number of system prompts and all the response handling is done in the agent(s).
It's terrible at hunting security bugs (I expected it to be, but I wanted to be sure). I added it to a benchmark I made with a corpus of some Mythos-discovered bugs, and it found zero. The smallest pretty successful models remain Qwen 3.6 and Gemma 4 (but I haven't tested the very small variants of those yet).
The lack of tool use will hinder it a lot I think, since bug hunting requires collecting context across a code base and stitching it together. It might be good in a more narrow sense, i.e "is there a bug in this block of code" and not considering how it interacts with the rest of the code base.
That's also more aligned to its leetcode style training data, the code under test is fully in the context window. It might be interesting to have a bigger tool use model go through the effort of collecting the context, and feeding it into this kind of model for analysis only. It becomes more of a thinking tool, instead of the orchestrator.
uberex 3 hours ago [-]
What is the idiots guude to run this one local now?
Landing7610 1 hours ago [-]
omlx makes it quite easy
yousif_123123 2 hours ago [-]
Use LM Studio.
unfirehose 2 hours ago [-]
this is a good model. I benchmark reasoned answers to qwen 3.6 27b (no think)+ bash and it held up.
4gotunameagain 37 minutes ago [-]
What are the implications of local SOTA inference, given the insane datacenter "investing" ?
It surely cannot be justified only for training at this scale, and since models nowadays are improved more and more by fine tuning than re-training from scratch.
Will a viable local model crash the US economy ?
More importantly, are the LLM companies aware, and are they deliberately buying out all the RAM and GPUs in order to prolong the inevitable ? Probably not, but I wouldn't be surprised if that is the case.
scotty79 6 hours ago [-]
If you could pair it somehow with a model that can code and describe code this could be a very powerful combo.
11 hours ago [-]
anonyfox 7 hours ago [-]
Wake me up when it does OCaml fine.
diseasedyak 16 minutes ago [-]
[dead]
jkwang 6 hours ago [-]
[flagged]
sosojustdo 11 hours ago [-]
[flagged]
riponcm 9 hours ago [-]
[dead]
lisa_luoyf 5 hours ago [-]
[flagged]
t_e_s_t 5 hours ago [-]
[flagged]
t_e_s_t 5 hours ago [-]
[flagged]
t_e_s_t 5 hours ago [-]
[flagged]
maxignol 5 hours ago [-]
3B param on par with opus 4.5 sounds interesting. Will read the full article before making my mind
zkmon 8 hours ago [-]
Does python coding depend on political facts of the world?
It might appear not, but actually, the process of reasoning is not an isolated act. The right and wrong way of doing things is codified in social evolution that absorbed all facets of life. Why should you optimize a piece of code for performance? Why performance is needed? What is a bug? What features and UI themes would be more intuitive for humans?
There is a butterfly effect. Everything affects everything to some extent.
spacebacon 7 hours ago [-]
[dead]
Rendered at 14:05:48 GMT+0000 (Coordinated Universal Time) with Vercel.
The Q8_K_XL MTP model from Unsloth: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Sadly that's not how LLMs work, since all they do is "token prediction". At least the models we have to today ...
Some amount of knowledge is required for reasoning. Maybe such model can dynamically knowledge domains to have taxonomy. For example, model can't effective reason about development task, if it has no knowledge about development best practices. But population of New York or recipies can definitely be loaded run time with tools.
This is the root of problem. If you think about STEM universities, they don't really teach you things you need in the real world. They teach you what you need to know in order to go out there and accumulate the necessary information which can then be used to solve problems. Giving a person access to the internet or a super powerful calculator (like Mathematica) won't mean that they can do anything useful. They need tons of experience to use these tools in an effective way. That experience is basically all that implicit adjacent knowledge that we pick up along the way getting our degrees. And LLMs pick that up during pre-training. Drop this part and the outcome will be worthless.
In my school, math teacher was giving me prose, which I was converting to math notation. I could argue, that this prose→reasoning conversion is not required at training, and can be obtained at inference time with search tools.
Our computers can already do everything, have access to all the tools and information, yet they still need a human/intelligence to use it and apply to specific problems.
Even defining the problem requires knowledge.
As for the tools, if the model has access to 1000 tools, how would it know which one to use if it doesn't have any knowledge itself?
What if I ask for "table tennis spin" it had a "magnus effect calculator", how would it know to make the connection between the two?
This is only one example, plus if the topic is more complex, maybe it had to search/learn everything (what is table tennis, what is spin, what is a human, what is a ball), etc. So it would be like spawning a baby human, have it spend an (instant) life learning about the world before providing an answer. Maybe this could work in 10 yesrs, if models get stronger with huge context lengths and almost instant data retrieval. Is it the best way to go about things though? Most animals have most of their core abilities embedded in their DNA and "instincts". A cat doesn't have to learn what a bird is in order to hunt it, it's already "embedded" in its neural pathways, or even deeper, at a full-body level. Those type of systems are a lot more efficient than the learned ones. Maybe the best future AI, will have everything already embedded, instead of just being a strong reasoning machine. All AI responses should be instant and like "reflexes" instead of reasoned steps.
If "all the knowledge" is what our models now do, what exactly would be the most extreme "none of the knowledge +search" ?
> language specifications.
It would load in all the knowledge to figure it what "language" means, then it would continue trying to decode what "specifications" means.
That might sound absurd, but to figure out the population of New York It's either: Just going to google it, or derive from primary sources.
But how is it ever going to interpret the primary sources? It needs to understand the question, how complex a question is, and how complete an answer is and how things relate. Thats just _too_ much language.
There might be a way to compact this down into a LLM-native language such that the request of `the population of New York` or `use best practices` is encoded without our messy human language for a reasoning model to work with, but the encoding itself has to be done by the "all the knowledge" llm. Now it seems we just rebuild something related to MoE with extra step afaict.
Turns out that without the world knowledge to have a base of facts, it is not.
So I don't think it's true that relevant knowledge was deprioritized. At least it wasn't supposed to be.
First, if you know nothing you don't even know what you're missing or what to search for.
Then, without unlimited context, you have to do research for every task all over again every time.
RAG on the initial prompt would be the first thing to try.
> Then, without unlimited context, you have to do research for every task all over again every time.
Thing is, we're really really good at building very fast search engines. Doing research all over again every time shouldn't be a problem.
Even the most basic questions such as put a ball in a cup and place it on a table upside down then pick up the cup and put it in a box.
Requires knowledge of things not mentioned in the question (notably gravity).
Strict definition of all terms quickly gets you into a quagmire of complexity. Some base level of knowledge about things is required for you to give it instructions. If it only knows how to reason, it lacks any idea of what to aim to achieve.
There is quite a pronounced disconnect between the vast stores of written data that models are trained on and robust consideration of a topic. I do wonder if the path can be directed by the order of training.
For example if you train a model to basic literacy using tinystories, then math and philosopy texts, then psychology, and sociology texts, and then finally the mass data of everything from conversations and rants, to code and fiction.
Does that end up with a significantly different model to one that is trained on books on acting, creative writing, and fantasy novels, before introducing the same final mass data set.
How much does it's current ability allow it to contextualise new training data?
I do not think this is a great example. First, it is not a question. Second, it seems very related to robotics. A model itself cannot put a ball anywhere, it can just call tools and answer in text, image, etc.
An LLM seeing "put a x in a y and place it on a z upside down then pick up the y and put it in a z2." and then a question about what happens could check a rag for properties of those x,y,z,z2 and still answer. Alternatively, this could be useful for coding, for example. And that is a very extreme example. Some basic language plus tool use could go quite far. I think it is a very interesting direction vs here is a gpu the price of a car.
That plus this model should give you a very powerful and focussed assistant.
Except for the most basic of tasks, such as "turn on my lights" or "cross-reference these two lists", I wouldn't trust a small model to be as conscientious and reliable as one with deep knowledge.
Even recent massive models do not work anything like a smart human does at the moment so why are we assuming this can?
Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
Small models need to have enough base knowledge to be able to be good enough -- even in a seemingly narrow regime. Where is that? Obviously they don't need all the obscure knowledge of a frontier model but there is some base level which is probably more than it would first seem.
Emphatically, it does not. Passing your drivers test may require being able to read, but plenty of illiterate people around the world drive just fine.
There is a reason we made all the common road signs recognisable purely by shape/colour, after all.
Though it is true you don't need to be able to read to operate a vehicle, you /do/ need to be able to read to operate a vehicle safely.
And for those who can read: could you teach someone how to drive using an LLM? Sure. Safely? Probably not.
[0] https://www.transport.nsw.gov.au/operations/roads-and-waterw...
Especially important in places like Europe, where it's common for the driver to be able to read, but unable to speak the language of the country they are currently driving through. I can't speak any Polish, but can travel on Polish roads just fine
1: https://en.wikipedia.org/wiki/Prohibitory_traffic_sign#No_en...
Then there is Hanoi.
Not really. You just need to be able to decipher the sign, which is trivial, even if you can't read it or spell it.
But in situations that could be ambiguous, I think this is a regional difference - the US, Australia, part of the rest of the Americas use lots of text on road signs (including literal "wrong way" signs); Europe and much of the rest of the world use far less text (including purely pictographic "wrong way" signs). Especially important in Europe where drivers just can't learn 20+ languages.
These signs, you mean? https://en.wikipedia.org/wiki/Prohibitory_traffic_sign#No_U-...
It's also trivial to do a u turn even when you can read, know what the sign says, and you feel like doing one because no car is coming anyway, and millions of people do that everyday too.
And whole lot of people have done stupid shit like that while perfectly able to read, many even with masters and PhDs.
It is really strange to see comments like this here, where people seem to reduce some basic human action into how it would work in a text-only computer game. Driving itself requires mainly muscular memory how to operate the car, which why people who drive a lot can just go on autopilot and think something completely different when driving long distances. That is of course a form of kno, but you only get it through repetition. Of course driving in traffic requires far more, basic understanding of traffic law etc, but most of driving is muscle memory, understanding the vehicle and anticipating future occurrences. Why we apes are so good at this is because we have some million years of evolution of just using our bodies and seeing what happens. And of course we all seen the gif of an orangutang driving a golf cart (how real it is I’m uncertain), so there’s that.
I think might help to think models not as some future replicants, but models with certain capabilities in certain domains. It probably doesn’t make much sense to ask Opus 4.8 to drive you around as it doesn’t make sense to except a small image model made for edge devices to be able to write a novel. Perhaps we should just think of them as tools with certain applications they are made for.
I would be interested to see a formal study of this. I say this not out of anything other than a observation that I think the only real blockers are a) judgement, and b) physical reflexes/strength. As a kid I was certainly aware of ice,snow, and rain, because I road my bike year round and had low confidence in my own ability to control my bike on snowy or wet terrain, especially during season changes. That translated into learning to drive in northern Canada in the winter and applying those lessons to driving.
In an environment devoid of consequences, I have seen kids operate driving simulations (both real simulations, and video games) with a degree of precision that is shocking, including seeing several 9-11 year olds play the simulations and games with a much higher degree of confidence than adult drivers. Children have an awareness that the simulations are consequence free, unless given other motivation. Adults that are consistent drivers have muscle memory and preconceived expectations that govern the decisions they make when playing the game. I am curious about the level of training and exposure required for children to overcome their lack of awareness of the hard limits and consequences of driving and driver error, versus the amount of training and exposure required for expert drivers that are novice gamers to stop applying their learned experience to consequence free simulations.
(i'm above average in both)
Different times though.
https://www.youtube.com/watch?v=BWAK0J8Uhzk
Millions of people do drive who can't read. It's very common in parts of Asia, Africa, Latin America, etc, especially rural, but even in cities.
There are places where oral exams and audio-assisted testing is allowed. And there are places where people just drive (and drive fine) not bothering with a license.
This requires not only knowledge, but also the control systems that develop with the prefrontal cortex. LLMs don't do much control yet.
Conflation. That's to drive a car safely. To just drive a car one only need know to press gas to move, press brake to stop, turn steering wheel to change direction and maybe use a gear stick to shift into drive/park (car can be modified to abstract that away). Not much more complex than riding a bicycle; maybe even less since no need to learn to balance.
Seems like a really good model to use in an IDE when you still want control over the code structure then.
I'm glad to see more domain-focused SLMs, we need more of them! A programming focused MoE should work well across many languages.
It is a cheap specialist for closed-world, verifiable reasoning tasks like math, self-contained coding problems, and similar.
"Closed-world" means the needed information is already in the context. It is not a tool-using agent that can discover missing context. "Verifiable" means answers are hard to generate but easy to check.
So no open ended research, repo wide agent work, factual Q&A, or SVG generation. More of a compact reasoning module for bounded problems.
The answer is exactly what you have posted. I am impressed by Qwen!
I just tried the quantized Q4_K_M from [1] in my RTX 2070 Super, it ran at 110 tok/s with 1800 tok/s prefill, and found the same solution to your prompt. It generated valid LaTeX for the answer but its reasoning trace uses mostly compact ASCII math notation. Took 3min 22s to answer, spending 22k tokens almost all on thinking.
[1] https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF
It's like web hosting; all the open source tools are there and free, and yet website tools, hosts, etc flourish.
SOTA providers are expecting some level of margin. Companies everywhere have a tight eye on their AI bills right now.
The motivation is there if the models get good enough, even if it’s more painful.
How?
So who has suggestions on small models with excellent tool calling capabilities?
> these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios.
These kinds of models might be more useful as tools to be used by larger orchestrator models, than being the orchestrators themselves.
Here's what I got
https://9ol.es/tmp/pelican.png
with https://9ol.es/tmp/prompt_pelican.txt
using prithivMLmods/VibeThinker-3B-GGUF:Q4_K_M
It would look really dumb if someone asked it that, but that's fine. You're trying to make a model that is optimized for efficiency for a specific task. As much as possible, you should prune uncorrelated things.
Assuming tool calling hasn’t been entirely stripped out of this model.
(Edit) No tool calling, per this comment: https://news.ycombinator.com/item?id=48640189
I really like the idea of small models that can reason but do not have too much knowledge. Also, no emphasis on tool calls. I think the agent should do the heavy lifting and reach half way.
I use really small models, like Qwen 3.5 0.8B to 9B - no tool calling, no MCP, no skills, nothing. No multi-turn chat even. Models are given very specific tasks using a vast number of system prompts and all the response handling is done in the agent(s).
https://github.com/brainless/nocodo
https://swelljoe.com/post/will-it-mythos/
That's also more aligned to its leetcode style training data, the code under test is fully in the context window. It might be interesting to have a bigger tool use model go through the effort of collecting the context, and feeding it into this kind of model for analysis only. It becomes more of a thinking tool, instead of the orchestrator.
It surely cannot be justified only for training at this scale, and since models nowadays are improved more and more by fine tuning than re-training from scratch.
Will a viable local model crash the US economy ?
More importantly, are the LLM companies aware, and are they deliberately buying out all the RAM and GPUs in order to prolong the inevitable ? Probably not, but I wouldn't be surprised if that is the case.
It might appear not, but actually, the process of reasoning is not an isolated act. The right and wrong way of doing things is codified in social evolution that absorbed all facets of life. Why should you optimize a piece of code for performance? Why performance is needed? What is a bug? What features and UI themes would be more intuitive for humans?
There is a butterfly effect. Everything affects everything to some extent.