FilterHN

1-Bit Bonsai Image 4B Image Generation for Local Devices

97 points

by modinfo

2 hours ago

| past

| 12 comments

| prismml.com

| HN

▲

jeroenhd

15 seconds ago

[-]

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.

▲

lumost

1 hour ago

[-]

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.

▲

neals

12 minutes ago

[-]

I'm curious how hardware and power cost would stack up to subscription cost

▲

bigmadshoe

35 minutes ago

[-]

Can you give an example of such a problem?

▲

sorenjan

1 hour ago

[-]

They call it a diffusion model, but it's based on Flux.2 which is a rectified flow model.

▲

iJohnDoe

1 minute ago

[-]

Does anyone ever get their stuff to actually work. Like actually load?

▲

wiradikusuma

51 minutes ago

[-]

Is there a benchmark of local image generation models? Local = can run on a 16 GB MacBook or 8 GB+ NVIDIA card.

▲

a1o

53 minutes ago

[-]

Anyone could pickup the minimal hardware requirements for this? Like both RAM and Storage?

▲

mkl

18 minutes ago

[-]

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.

▲

a1o

1 minute ago

[-]

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…)

▲

sudb

26 minutes ago

[-]

Very interested to see where this kind of work goes for on-device video generation!

▲

potatoman22

33 minutes ago

[-]

I wonder why they didn't use a Bonsai model as the text encoder

▲

MitPitt

1 hour ago

[-]

Lately I've noticed posts with barely 10 points getting to HN frontpage. Was it always like this?

▲

robbomacrae

1 hour ago

[-]

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.

▲

s-macke

1 hour ago

[-]

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.

▲

blurbleblurble

28 minutes ago

[-]

Maybe the algorithm has some kind of "momentum" to it, taking into consideration the velocity of upvotes.

▲

nickvec

35 minutes ago

[-]

If you are looking to see the "true" HN frontpage (i.e. most upvoted posts), I'd recommend using https://hckrnews.com

▲

DannyPage

1 hour ago

[-]

Not as much competition on the weekend?

▲

Aboutplants

1 hour ago

[-]

I just assume bots

▲

iamjackg

1 hour ago

[-]

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?

▲

speedgoose

41 minutes ago

[-]

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.

▲

janniks

35 minutes ago

[-]

I was expecting to see images of Bonsai trees when I clicked this

▲

tobr

34 minutes ago

[-]

I expected a small tree in black and white pixel art.

▲

SilentM68