alt Hacker NewsThe big story here is the encoder-free part, which I still don't fully understand.
> Vision: We replaced Gemma 4’s vision encoder with a lightweight embedding module consisting of a single matrix multiplication, positional embedding and normalizations.
That's technically encoding, just without using a dedicated model for it like SigLIP? The Developer's Guide elaborates, it's still a 35M layer which I am curious is robust enough. https://developers.googleblog.com/gemma-4-12b-the-developer-...
> Small enough to run locally on consumer laptops with 16GB of RAM, it unlocks powerful multimodal and agentic experiences right on your machine.
I am assuming that involves quantization, which due to the quality loss makes that statement somewhat misleading IMO.
Replies
Embedded within that developer page is a good explainer of the encoder free architecture . https://newsletter.maartengrootendorst.com/p/a-visual-guide-...
The audio side is even more interesting, as it seems they totally got rid of positional embedding are just doing a single linear transform to match the LLM input dimension and that's it.
> Audio: We simplified audio processing even further. We removed the audio encoder entirely and projected the raw audio signal into the same dimensional space as text tokens.
Totally agree that it is "encoding" in the general sense, but I think they are referring to the lack of an "encoder" neural network.
> quantization
12b means 12G @ 8 bits/param (basically lossless) and 6G at 4 b/p (generally accepted 'pretty close' level). Not too bad?
But TBD how well the base model performs before thinking too much about quantization
One side-effect, is that the separate .mmproj file (Multi-Modal Projection encoder) is no longer needed, when using the model with llama.cpp etc.
There are many priors to encoder-free VLMs. I specifically remember the EVE series of models from ~2 years.
Encoder free is huge for running on SBCs etc. often the encoding time is a significant fraction of generation time if you are using a VLM as a all purpose vision model
It actually works well because unlike encoders, the latent space is trained on that initial layer so it “knows” what to do with that sparse density. I’ve been using gemma4-12b with Flux2 and its ability to reason on visual input is pretty good. That said, each model is good in their own ways so YMMV but overall, it’s about as solid as Qwen just with a more advanced architecture.
I think the idea is that the model is seeing embeddings that map directly to underlying pixel data, rather than being fed semantically rich embeddings from an encoder model which itself had seen the raw pixel data.
Well its a real simple encoder I guess
> That's technically encoding
Isn't that just projecting the patches into the d_model size vectors that the models takes?
>I am assuming that involves of quantization
12B model in 16GB seems very reasonable to me, int8 is top quality for running models.
[dead]
This is just early fusion basically.
FAIR did this 2 years ago now: https://arxiv.org/abs/2405.09818
I've been waiting for something like this to be released since then.
The annoying thing is that chameleon was multi-modal out based on the same principles, but this model is just inputs... (I'm curious how they did pre-training without having multi-modal outputs as well. I wonder if they just chopped them off rather than support image output).