IME, the bottleneck when using diffusion models isn't storage space or memory, it's generation time. Lots of models will run on 8-12 GB 1080-generation GPUs onwards, or on Macs with similar memory, which are probably the bottom end from a GPU power perspective anyway. I also note that these models are marginally slower than the small FLUX.2 model they're based on.
Okay, maybe this allows running a local model on something that has a reasonably powerful GPU and limited memory, like an iPhone, but is that really a common requirement?
Just a side note, that this website is classified by Apple as an Adult website. I have Limit Adult Websites set in Content & Privacy Restrictions switched on.
Led me to wonder what happens if a domain gets a new owner, and they want to petition Apple to remove the block.
I actually can’t wait for the future where I upgrade hardware in order to upgrade my ai as an alternative to an expensive subscription.
There are many problems I want to work on which require billions of tokens. These are completely inaccessible without corporate project sponsorship at the moment. An asic generation machine which can pump out a few 10s of thousands of tokens per second at opus4.6 quality is more than sufficient.
A company called Taalas is working on something like that. Not Opus4.6 quality, but I'm sure they're targeting larger models. Currently they're using a LLama 8B model. It runs at ~17k tokens per second, and you can test it at https://chatjimmy.ai/.
Couldn't try it because the demo app is iOS only and the web version just crashes my browser. The small model is impressive but if you front load a 1.8GB text encoder model, the savings aren't quite as useful.
what trade off would one need to clear to justify the hardware and the work to get this running locally as part of a broader system? It’s a lot of work setting up and maintaining a production harness/system on a local device. I don’t personally repeatedly generate images at a scale where using a lab’s app somehow burns all my tokens. I like the ideas of local ai but I don’t see widespread adoption of it happening in commercial or customer situations anytime soon no matter how little/good enough they get. Even Uber- token burn whiplash but I doubt their answer will be “run some of it local”. IT nightmare, I’d imagine.
The white paper says "mean-active memory pressure down to 1.95 GB for 1-bit Bonsai Image 4B and 2.38 GB for
Ternary Bonsai Image 4B". Storage is on the linked page, and is about half that.
That is very low, looks like it should run in base MacMini M4 with 16GB RAM. I understand it is not released yet? What sort of harness is necessary for this type of model? (I have only used coding agents through GH Copilot in VS Code, the JetBrains AI tool and Pi, this last one was sort of a pain to setup…)
I believe it's the way the HN algorithm works. In order to give new and obscure posts a shot, it will add them to peoples feeds in their front page and see how they measure. Otherwise new posts wouldn't get seen and the flywheel would never get started.
So everyone acts as a sort of beta tester for obscure posts.
On weekends, yes. During the week, that’s also true if they arrive within a short time frame, e.g., three minutes. Almost no one looks at “New”. That is the real issue.
It’s about how quickly they get those points. It doesn’t have to be bots. Sending a post to friends with reputable human profiles, and asking for a vote kinda works of most social networks. Some social networks claim they have protection against this but I wouldn’t bet they catch everything.
The online demos require WebGPU so Firefox on mobilr and privacy enhanced browsers will break. WebGPU support on Linux and other open source systems is also trash, you can force it to work in Chrome but it won't be happy.
Genuine question: is this solving a real problem?
IME, the bottleneck when using diffusion models isn't storage space or memory, it's generation time. Lots of models will run on 8-12 GB 1080-generation GPUs onwards, or on Macs with similar memory, which are probably the bottom end from a GPU power perspective anyway. I also note that these models are marginally slower than the small FLUX.2 model they're based on.
Okay, maybe this allows running a local model on something that has a reasonably powerful GPU and limited memory, like an iPhone, but is that really a common requirement?
Just a side note, that this website is classified by Apple as an Adult website. I have Limit Adult Websites set in Content & Privacy Restrictions switched on.
Led me to wonder what happens if a domain gets a new owner, and they want to petition Apple to remove the block.
I actually can’t wait for the future where I upgrade hardware in order to upgrade my ai as an alternative to an expensive subscription.
There are many problems I want to work on which require billions of tokens. These are completely inaccessible without corporate project sponsorship at the moment. An asic generation machine which can pump out a few 10s of thousands of tokens per second at opus4.6 quality is more than sufficient.
A company called Taalas is working on something like that. Not Opus4.6 quality, but I'm sure they're targeting larger models. Currently they're using a LLama 8B model. It runs at ~17k tokens per second, and you can test it at https://chatjimmy.ai/.
I'm curious how hardware and power cost would stack up to subscription cost
Can you give an example of such a problem?
To our knowledge, Bonsai Image 4B is the first image model in its parameter class to run directly on an iPhone.
Isn't SD XL 3.5B? And the refiner model is even larger. Those can run on an iPhone 13 Pro.
Couldn't try it because the demo app is iOS only and the web version just crashes my browser. The small model is impressive but if you front load a 1.8GB text encoder model, the savings aren't quite as useful.
I do wonder how these compare to existing image generation models. I've tried https://github.com/alichherawalla/off-grid-mobile-ai for a while but I find the image generation models rather lacking.
They call it a diffusion model, but it's based on Flux.2 which is a rectified flow model.
what trade off would one need to clear to justify the hardware and the work to get this running locally as part of a broader system? It’s a lot of work setting up and maintaining a production harness/system on a local device. I don’t personally repeatedly generate images at a scale where using a lab’s app somehow burns all my tokens. I like the ideas of local ai but I don’t see widespread adoption of it happening in commercial or customer situations anytime soon no matter how little/good enough they get. Even Uber- token burn whiplash but I doubt their answer will be “run some of it local”. IT nightmare, I’d imagine.
Is there a benchmark of local image generation models? Local = can run on a 16 GB MacBook or 8 GB+ NVIDIA card.
Anyone could pickup the minimal hardware requirements for this? Like both RAM and Storage?
The white paper says "mean-active memory pressure down to 1.95 GB for 1-bit Bonsai Image 4B and 2.38 GB for Ternary Bonsai Image 4B". Storage is on the linked page, and is about half that.
That is very low, looks like it should run in base MacMini M4 with 16GB RAM. I understand it is not released yet? What sort of harness is necessary for this type of model? (I have only used coding agents through GH Copilot in VS Code, the JetBrains AI tool and Pi, this last one was sort of a pain to setup…)
For ternary mlx, size on disk is 3.8GB. 512x512 peak memory use is ~3.7
The text encoder is still 4-bit quantized.
Very interested to see where this kind of work goes for on-device video generation!
Lately I've noticed posts with barely 10 points getting to HN frontpage. Was it always like this?
I believe it's the way the HN algorithm works. In order to give new and obscure posts a shot, it will add them to peoples feeds in their front page and see how they measure. Otherwise new posts wouldn't get seen and the flywheel would never get started.
So everyone acts as a sort of beta tester for obscure posts.
On weekends, yes. During the week, that’s also true if they arrive within a short time frame, e.g., three minutes. Almost no one looks at “New”. That is the real issue.
Maybe the algorithm has some kind of "momentum" to it, taking into consideration the velocity of upvotes.
Not as much competition on the weekend?
If you are looking to see the "true" HN frontpage (i.e. most upvoted posts), I'd recommend using https://hckrnews.com
I just assume bots
Bots doing what? How would the poster being a bot influence why the post itself makes it to the front page with just 10 points?
It’s about how quickly they get those points. It doesn’t have to be bots. Sending a post to friends with reputable human profiles, and asking for a vote kinda works of most social networks. Some social networks claim they have protection against this but I wouldn’t bet they catch everything.
I wonder why they didn't use a Bonsai model as the text encoder
I was expecting to see images of Bonsai trees when I clicked this
I expected a small tree in black and white pixel art.
Does anyone ever get their stuff to actually work. Like actually load?
The online demos require WebGPU so Firefox on mobilr and privacy enhanced browsers will break. WebGPU support on Linux and other open source systems is also trash, you can force it to work in Chrome but it won't be happy.
Question,
Is it compatible with Ollama, ComfyUI or are those providers unneeded, compatible with low-end hardware?
Also, where does "./setup.sh/ drop the components in Linux?
Thank you, Sol
impressive, combines a couple techniques that I always wanted the frontier models to have
having trouble loading the webgl browser demo on my phone but no biggy