Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemma 4 12B: A unified, encoder-free multimodal model

blog.google

Post reply on HN
Print view View original

141–150 of 421 posts

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#141

Post by asim »

georgehm wrote: post #53
minimaxir wrote: post #2

The 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 ro…

Embedded within that developer page is a good explainer of the encoder free architecture . https://newsletter.maartengrootendorst.com/p/a-visual-guide-...

That's a great explainer, thanks for sharing it.

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#142

Post by minimaxir »

dofm wrote: post #127
minimaxir wrote: post #2

The 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 ro…

I would contend that the actual big story is the gallery app: https://developers.google.com/edge/gallery Anyone with a 16GB Mac — that is quite a lot of journalists, surely — can download that, install a model into it, and play. Surely journalists have to start asking questions at least about OpenAI's consumer revenue projections now. I am a major, major AI cynic, but I decided to be an informed cynic so I've been pl…

I had discounted Edge Gallery because it didn't support system prompts, but now it does so I will give it another go. I believe the implementation does use MTP since I got an update to Gemma-4-E4B on iOS indicating such, and on macOS it's very speedy.

However, on my 18GB RAM MacBook Pro, selecting Gemma-4-12B-it results in this error:

> The model "Gemma-4-12B-it' requires more memory (RAM) than is available on your device.

So yeah, my questions about the 16GB marketing copy are fair.

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#143

Post by mchusma »

anonova wrote: post #135

Do Gemma 4 models compete with Gemini 3.1 Flash-Lite? I would assume even the smallest Gemini model would outperform even Gemma 4 31B, but I can't really get a sense of performance or output quality difference.

Gemma 4 31b outperformed Gemini 3.1 Flash-Lite in our app benchmarks (agentic tool use via api in our application as a part of various workflows). But google won't let you pay to use Gemma models, you have to go elsewhere, I think this may be because it would cannabilize Flash-lite.

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#146

Post by verdverm »

ethanpil wrote: post #13

What's Google's business case for releasing open models? Don't get me wrong, I am grateful and appreciative of these releases. I'm trying to understand how it fits into their bigger picture as a for profit company? Are they not helping competitors build on the novel technology they have developed? Is it simply goodwill and/or marketing? Or am I missing something strategic?

Competition from Chinese alternatives hopefully forces more openness and efficient models. DeepSeek for example is nearly on par and far more resource efficient, good for the planet imo

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#147

Post by powera »

I'm seeing very low quality results on LMStudio with this model. Worse than Gemma 3 12B.

It is getting questions like "David has 18 apples and Ivan has 7 apples. How many apples do they have together?" wrong half the time, while Gemma3 12B could very consistently answer that. Other smoke tests (like Chinese translation, and the infamous "Rs in Strawberry" test) also show poor results.

I don't know if it is a quantization/release issue, if the parameters needed for accurate responses have changed (i.e. it needs "thinking" tokens to handle its base error rate), or if the model has been so focused on audio/video that the text processing is bad.

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#148

Post by frikk »

senko wrote: post #120

I ran the Q4 quant (used with llama.cpp) though my "minesweeper" vibe-coding benchmark: https://senko.net/vibecode-bench/2026/minesweeper-gamma-4-12... The result is decent, but it had a few bizzare/trivial syntax errors I had to fix manually: it would do an extra closing bracket or paren a few times, and wanted to separate function definitions with comma. Not sure what that was about, but otherwise the output run ju…

Thank you for sharing this. Do you think the syntactical issues could be addressed with fine tuning or some other kind of parameter tweaking? That's frustrating hah.

Re: Gemma 4 12B: A unified, encoder-free multimodal model

#150

Post by verdverm »

julianlam wrote: post #128

Last time I tried Gemma 4 (26B-A4B) its memory usage would balloon and consume all of my swap until my machine died. Qwen 3.6 on the other hand barely uses any memory at all for its KV cache.

Turns out when you block people from the best and biggest hardware, they get innovative. It reminds me of the Pentium days when everyone was shipping inefficient programs because the processor would be better next year.
Post reply on HN