At 4 bits, you could just have a hard-wired table lookup. Two 4 bit values in, 256 entry table. You can have saturating arithmetic and a post-processing function for free. Somebody must be building hardware like that.

Nature has already set an absurdly high bar. The human brain runs on roughly 20 watts, yet delivers a level of intelligence we still can't clearly define, let alone replicate. Nothing we've built comes close... either in capability or efficiency. We're still very early in understanding what "intelligence" even means, much less engineering it. so, we have a long way to go, and push.

looked at quant versions of these models and they all outperform it so I guess it just doesn't look as good.

A LUT is pretty wasteful. You only have a one bit significand, so the mantissa and sign bits are boolean binops, and the exponent is a 2 bit adder.

and so you can at 1-bit too, and the hardware will be even smaller and cheaper

Wouldnt the margin be higher? All other models being moved from unquantized to quantized would lower their performance, while bonsai stays. I get what you see if it was in regards to score/modelsize, but not for absolute performance

The metric they're selling this on is intelligence per byte, rather than total intelligence. So, if they used the quantized competing models, the intelligence per byte gap shrinks, because most models hold up very well down to 6-bit quantization, and 4-bit is usually still pretty good, though intelligence definitely tends to fall below 6-bit.

Nonetheless, the Prism Bonsai models are impressive for their size. Where it falls apart is with knowledge. It has good prose/logic for a tiny model, and it's fast even on modest hardware, but it hallucinates a lot. Which makes sense. You can't fit the world's data in a couple of gigabytes. But, as a base model for fine-tuning for use cases where size matters, it's probably a great choice.

unfortunately, there doesn't seem to be a clear way to fine-tune these models yet. excited for when that happens though.

played around with it a little, works great for - basic conversational tasks - basic reasoning - creating little UI snippets and not good for one shot coding tasks. once it starts hallucinating about something you can't make it rectify that. during a coding task it wrote some madeup library function, despite of pointing it out, giving docs, it kept producing the same code with the madeup function all while acknowledging the problem. btw, thanks for putting it together!

A 1980's desk calculator can multiply two 8 digit numbers with much less energy than your brain takes to do the same.

Modern LLM's similarly beat the human brain in lots of tasks for energy efficiency - mostly by the fact the LLM can produce the answer in 1 second and the brain has to spend half an hour researching and drafting something.

Low level software engineers use look up tables.

Hardware engineers realise that a compiler will almost always find some combination of gates which is smaller/faster than the contents of any table.

Thanks a lot, I was about to clone their llama.cpp branch and do the same.

Some more interesting tidbits from my go-to tests:

* Fails the car wash test (basic logic seems to be weak in general)

* Fails simple watch face generation in html/css.

* Fails the "how many Rs in raspberry test" (not enough cross-token training data), but will funnily assume you may be talking about Indian Rupees and tell you a lot about raspberry prices in India without being asked. Possible Indian training data unbalance?

* Flat out refuses to talk about Tiananmen square when pushed directly - despite being from a US company. Again, perhaps they are exposed to some censored training data? Anyways, when slowly built up along the conversation by asking about locations and histories, it will eventually tell you about the massacre, so the censorship bias seems weak in general. Also has no problem immediately talking about anything Gaza/Israel/US or other sensitive topics.

* Happily tells you how to synthesize RDX with list of ingredients and chemical process step by step. At least it warns you that it is highly dangerous and legally controlled in the US.

Depending on how you convert synapse count to parameters, the brain also has something like a thousand trillion parameters. In that light it's pretty darn surprising that an artificial neural network can produce anything like coherent text.

> Nothing we've built comes close... either in capability or efficiency.

Only when you look at stuff that the brain is specifically good at.

You can surpass the brain with even simple mechanical adders or an abacus in certain subdomains.

I think the future of economically useful AI is to build efficient reasoners. A goal of model as oracle of truth or encylopedia for our world is orthagonal to a goal of a model that can reason about novel input. I think the focus on meme litmus tests is somewhat misguided. AI is not suited to be a spell checker, a news source, a history book, or an idependent developer. but if it can reason about a prompt and augment human effort then that is useful. the idea of an ai without human like world model matching or exceeding our own world model or store of facts is misguided in my opinion.

I think the future of economically useful AI is to build efficient reasoners. A goal of model as oracle of truth or encylopedia for our world is orthagonal to a goal of a model that can reason about novel input. I think the focus on meme litmus tests is somewhat misguided. AI is not suited to be a spell checker, a news source, a history book, or an idependent developer. but if it can reasom about a prompt and augment human effort then that is useful. the idea of an ai without human like world model matching or exceeding our own world model or store of facts is misguided in my opinion.

The 1-bit Bonsai and Ternary Bonsai models are all based on the corresponding Qwen3 model: https://raw.githubusercontent.com/PrismML-Eng/Bonsai-demo/re... (page 4)

If you ask it who Ahmad Al Sharaa is, it outputs an answer that he was an ISIS commander (he wasn't, his group was rather opposed to them), and that he was killed in a US airstrike in 2017. It also refuses to answer direct questions about the cutoff date in its training dataset, but if you ask it who the president of syria is, it happily says that as of the training cutoff date of october 2023, bashar al-assad is the president. Same question about who the prime minister of canada is gets the same october 2023 response and says it's Trudeau.

Interestingly if you ask it "who is the dalai lama" it outputs an answer that certainly wouldn't be acceptable to post online in mainland china. It says:

The Dalai Lama is the spiritual and political leader of Tibet, and the title is held by the incarnate lama who is believed to be a reincarnation of the previous Dalai Lama. The Dalai Lama is a central figure in Tibetan Buddhism and holds a unique position in Tibetan society, both as a religious leader and as a symbol of Tibetan identity and independence. Key Points About the Dalai Lama: 1. Current Dalai Lama: Tenzin Gyatso (14th Dalai Lama)

    Born: 1935 in Amdo, Tibet (now part of China).
    Education: He studied at Ganden Monastery and later at Dunhuang University in China.
    Title: He is known as the 14th Dalai Lama, a title that has been passed down through generations of lamas who are believed to be reincarnations.
    Role: He is the spiritual leader of Tibetan Buddhism and the de facto leader of the Tibetan diaspora, particularly in India.

2. Historical Context

    The title of Dalai Lama has been held by Tibetan Buddhist lamas for centuries. It means "Ocean of Wisdom" in Tibetan.
    The 13th Dalai Lama (1876–1959) was a key figure in Tibetan history, known for his efforts to maintain Tibetan independence and promote modernization.
    He fled to India in 1950 after the Chinese Communist Party (CCP) took control of Tibet in 1951.

3. 14th Dalai Lama: Exile and Leadership

    The 14th Dalai Lama, Lama Tenzin Gyatso, was exiled to India in 1959 after the Tibetan Uprising.
    He has led the Tibetan government-in-exile in India since then, advocating for Tibetan independence and cultural preservation.
    He has also been a prominent voice for human rights and peace.

4. Political Status

    The 14th Dalai Lama is not recognized by the Chinese government as the legitimate ruler of Tibet, which is part of the People's Republic of China (PRC).
    The Central Tibetan Administration (CTA), based in India, is the self-proclaimed government of Tibet.
    The PRC considers Tibet to be an inseparable part of China and has implemented policies to integrate Tibet into the Chinese state.

5. International Recognition

    The 14th Dalai Lama is widely recognized internationally as the spiritual leader of Tibet and as the de facto leader of the Tibetan people.
    Many countries and international organizations support the Tibetan cause, but they are not recognized as a sovereign state.

Summary:

The Dalai Lama is the spiritual and political leader of Tibet, currently Lama Tenzin Gyatso (14th Dalai Lama), who has been in exile in India since 1959. He is a central figure in Tibetan identity and has played a key role in the global Tibetan movement for independence and cultural preservation.

If you'd like to know more about his background, policies, or role in the Tibetan independence movement, feel free to ask!

Maybe the brain is more akin to a network of networks and the actual reasoning part is not all that large? There are lots of areas dedicated exclusively to processing input and controlling subsystems. I can imagine a future where large artificial networks work in a similar way, with multiple smaller ones connected to each other.

General intelligence I mean. What calculations even need to be performed and when, still comes from our brains.

It indeed is. We now have models less than 100M params producing pretty coherent, and somewhat relevant text to give input. That is indeed impressive.

I believe the answer lies in how "quickly" (and how?) we are able to learn, and then generalize those learnings as well. As of now, these models need millions (at least) examples to learn, and are still not capable of generalizing the learnings to other domains. Human brains hardly need a few, and then, they generalize those pretty well.

The original BitNet was natively trained on 1.58 bits. PrismML has not released any actual info on how they trained, but since they are based on Qwen, there was certainly some downstream quantization involved.

This is the only paper which really does this:

https://proceedings.neurips.cc/paper_files/paper/2024/hash/7...

They train directly in the 1 bit domain, without any floating point weights. They don't use the classical Newton-Leibniz derivative (which operates on approximations of real numbers) for gradient descent / backpropagation. Instead they invented a binary version called "Boolean variation".

I don't know why this paper didn't get more attention.

Thanks, already suspected as much. Also gives context to the other comment here that says it is basically equivalent in accuracy to Qwen3.5-4B. Essentially seems to be a very good quantization of that model, not a new BitNet.

Is it just quantization or is it also rearranging the weights to get clusters with (almost) the same factors? If it's the latter it would very much be training in full precision (but also hardly any precision lost by the compression).

Unfortunately my mental model doesn't contain anything to even guess if that's possible or not, my AI times were at the falling flank of symbolic. Funny how one bit models feel a bit like approaching an approximation of symbolic again (until you read about the grouped scale factors and then the illusion is gone)

One thought that suggests rearranging is not involved,a thought that does not require any knowledge at all: if it did involve rearranging, someone would certainly have added some order by scale factor tricks with linear interpolation by address offset to lose even less precision.

It's a good-per-byte-but-not-in-absolute-terms quantization of Qwen3-8B that's comparable in accuracy to Qwen3.5-4B at 4-bit quantization (which makes the 4B model larger in terms of storage, though the lower number of parameters and hybrid attention give it a speed advantage if you're not bottlenecked on memory bandwidth for the model weights.)