Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Anyone compare this to ternary bonsai vs the 1 bitby getcrunk
- I haven't compared it for perf, but at first glance this appears to be an LLM (text-only) while both binary and ternary bonsai 27B models are VLMs (where the vision tower and the adapter MLP weights are unquantized and kept in float16).
- Looks promising though much like the bonsai tenary one it hallucinates knowledge quite aggressively. The online chat having search tools covers this up somewhat, but it's still there.
...from very unscientific casual vibes it does seem pretty good though considering the speed
Would also be curious what their search tool backend looks like - that too is very fast for very rapid multiple searches
by Havoc - Makes me wonder how much we can 'get away with' in terms of raw model capability, when you have tool access for anything specialised or specific.
I probably could make up a bit of an incorrect carrot cake recipe if asked on the spot, but with a Google search I can give you something far more robust.
Maybe we don't need a 'country of geniuses' in our pocket, but more a helpful assistant that can reasonably reason!
by zooloo99 - My question is what LLM the author used for dev the web page? Maybe Claude? or ChatGPT?by vfalbor
- As of now, 3 of the 5 comments on this page are just 0-1 karma accounts high-fiving the article. Suspicious.by jsphweid
- You can play with it online. I was pretty impressed with the speed/quality given it's size.
It's definitely not going to replace a larger frontier model, but it's worth keeping an eye on.
by netghost - In mice. I mean Mac Mini M4 not an iPhone.
Also I love AI sites. Fancy font, plain serious style, we "introduce" rather than "release". It's an AI not an animal after all.
by hahahaa - At this point I think Apple just needs to simply not do anything stupid and these small model makers are going to hand them modelsby momojo
- >"At ultra-low bitwidths,
matrix multiplication can be effectively replaced with additions
, lowering the total arithmetic workload needed to infer through a model."
Interesting! I never knew that before... I will have to do some more research on this, but yes, it definitely sounds possible!
(Also (and this is just a wild guess/hunch here!)
in theory, matrix multiplication could be replaced with pre-computed cached lookups from a lookup table in memory
if, if and only if the resultant pre-computed lookup table of result matrices could fit into memory available!
In other words, think of a Matrix not as a 2D array, but as a 1D string. Think of the Matrix multiply operation as first appending the 1D string of the first matrix to the 1D string of the second matrix, then using that string as a Key to look-up a precomputed result in Memory...
Of course, the limitation to this approach is the availability of memory relative to the permutations of input values... It could work -- but only for smaller matrices... which leads to another strange idea... in that set of pre-computed matrix permutations, there might be duplicates... figure out a way to put duplicates in memory only once (could use pointers or some other scheme to do this) and you could theoretically store more matrices in the same memory and/or slightly larger matrices!
Anyway, just rambling out loud! :-)
Remember, "almost all programming can be viewed as an exercise in caching" to quote the legendary programmer Terje Mathisen! :-) )
Anyway, great article!
- “Current approaches to low precision primarily focus on converting models trained in full precision to lower bitwidths. We view this as fundamentally the wrong approach…”
Very excited to see how it performs, I’ve been a bit skeptical of the efficacy of converting existing models - really cool to see one trained from scratch in the ternary format.
by kamranjon - A benchmark table comparing to Qwen 3.5 35B-A3B seems strange when Qwen 3.6 35B-A3B has been out for some time and is significantly better.
I didn't notice the version difference when first reading the article! So this is a heads up to people like me.
- Their main comparison is 1-bit Bonsai 27B (Qwen3.6 27B) which beats A3B anyway.by ricardobeat
- For small models like this, it’s super important that it works well at tool calling etc. imho because it can’t memorize facts and isn’t big enough to tell when it doesn’t know. I could use it for high quality tool routing or a backup fast model for smaller task set. E.g. I use GPT-5.6 for voice channels at home. I’d prefer to be able to have this do basic tool calls and stuff because of the local speed.
Will give it a crack as a quick model in my clawlike.
by arjie - This matches what I've seen shipping Apple's on-device model in a Mac app.
The model is reliable at the semantic half. Give it the OCR text of a receipt and it correctly identifies the vendor and the date. What it does not do reliably is follow mechanical instructions. A user asked for dates formatted as TT-MM-JJJJ and got files literally named TT-MM-JJJJ, because it reproduced the format string instead of filling it in. Another asked for uppercase, and the model acknowledged the request in its reasoning and returned lowercase.
The failures were not consistent, which is worse than failing every time. You cannot tell users "this doesn't work", only "this works most of the time", and nobody accepts that from something touching their files.
What fixed it was moving the mechanical part out of the model entirely. The model decides what the document is about; ordinary deterministic code decides how the name is written. Every time I moved that line back toward the model, quality dropped.
Which is a version of your point: with a small model the win isn't making it smarter, it's shrinking what you make it responsible for.
by sdiazthomas - The most interesting thing is the "dreaming" idea for on-device adaptation. I guess regularly adjusting weights becomes possible when the model is so small and the math is simplified.
I'm assuming that doesn't actually exist yet, though, as I don't see anything about an implementation in the code that's been released.
But, it's a really interesting idea for a personal model. There's a risk of more AI psychosis if these things actually start "learning", but the value of it is also probably pretty big. I'm not sure I buy it will actually be able to self-improve, though. The best models are helping improve themselves, but the best models are considerably smarter and more capable than this one. I've asked models like Gemma 4 31B to help figure out training and synthesizing data, and it mostly fails on anything more than categorization and summarization. This little model is much dumber than that.
So, I'm skeptical, but maybe there's deterministic tooling that can assist and maybe it will be scoped tightly enough to just learn and update facts and not so much try to retrain the whole thing.
by SwellJoe - I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning.
"please write 250 words on the etymology and history of the word schlong"
The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish communities.
For comparison qwen 3.6 35B A3B does perfect on this and will give a solid description of the word's real origins and how it has made it into casual profanity/vulgarity as used in US English, and even mentions specific stand-up comedians and famous public figures of specific ethnic/religious origin in the US NE who introduced it into wider use.
Ask it for something that's not a narrow niche scientific or technical field, but something that would be less common to make it into a 20B size model, and see just how it does.
chat test link: https://chat.deepgrove.ai/
by walrus01 - They are not incorrect. They don't even hold a position in the first place.
An LLM continues the prompt it is given. What is more likely to come after a question? An answer, not an "oh sorry I'm not sure". Sure, you could make the latter more likely, but then the model would be unusable. Larger models simply contain more answers, more ways to stumble into them, and a granular enough geography to stay on the trail.
- lol I like the first one though. Reads like a great sarcasm response.
I wonder if kids will do this to their parents.
- Seems like less of a problem in smaller models where bullshit tends to become very obvious to anyone with half a clue about the given subject than it is in larger models where the illusion is complete enough that the confidently stated answers are very incorrect in more subtle ways.by boomlinde
- The schlong test is nearly as funny as drawing shit on bicycles test
- Small or overly quantized LLMs are a genre of humor. Same goes for small image generators. Janky generative AI is like the Geocities web pages of today.by api
- English Wikipedia: "As of 16 October 2024, the size of the current version including all articles compressed is about 24.7 GB without media."
Models in this size range should aim for correct tool calling and avoiding hallucinations, not universal knowledge. (apparently they don't.)
by hrmon - Would it not be better to ask models to search the topic on the Internet and then answer? I do not understand why we expect small LLMs to answer from own knowledge.by brainless
- I think for smaller models, they need to be more defensive on unknown information and frontier model level tool calling capabilities.
LLMs are kind of a compact knowledge box of its training data and it's understandable it would not have information about every topic and in that case just do a web search or a proper tool invocation to get the data and then synthesize.