A small dense multimodal model with audio support, interesting.
Wait, *Excluding Chinese language.
This is ... curious.
P.S. Where is gemma 4 124b?
Gemma 4 12B: A unified, encoder-free multimodal model
111–120 of 421 posts
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#112Are there qwen or minimax or other open weight models of same hardware requirements that outperform this?
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#113Earlier quoted context omitted.
Neutering OpenAI and Anthropic would be my guess. Commoditized LLMs won't hurt Google nearly as much as it hurts the LLM-only companies, and so accelerating the inevitable just helps knock out potential future competition in areas where Google -does- make a lot of money now.
I think this plays a part, but the truth is that Google doesn't need to do that, Chinese open models are already doing that by themselves. So perhaps another part is just Google showing that they can indeed play at the big boys table.
There is demand for US open models.
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#114I don’t see the download in lm studio
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#115Earlier quoted context omitted.
Android and Chrome need on-device AI capabilities. Google can't lock down those weights like it can with server-side ML. So it's easier to just release those models as open source and make it official, since someone would inevitably hack the weights out anyway.
Could say the same for camera processing in the Pixel Camera app or any other binary someone wants to re-use that comes included in a software distribution (seemingly for 'free'). They can't lock the instructions up on the server so they might as well make the binary be freely distributable? Companies don't commonly give away executable binaries "just because", why'd they start now for these binary blobs that are the…
Binaries are source code outputs, they are copyrightable and patentable. Weights are not copyrightable so people can freely extract the weights and run them. If Google patents any of the novel algorithms here releasing it all freely isn't an impediment to making people license it.
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#116Earlier quoted context omitted.
at risk of quoting myself... :) > By offering frontier inference closer to cost *and* open-sourcing everything that's sub-frontier It's two prongs! One prong is that their frontier inference pricing is significantly cheaper/closer-to-at-cost as Anthropic's. The subject of this thread is the other prong: offering compelling models that are sub-frontier and self-hostable. Self-hosting models and at-cost frontier models…
Google needs an anti-trust breakup about 10 years ago. They need one more than ever now. This is ridiculously anti-competitive.
This is literally competition
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#117The 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…
> 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.
I don’t think so, the HF weights are bf16 which means 24GB + cache/overhead.
It sounds like marketing spin where the performance claims are based on BF16 and the “runs in 16GB” claim is on a totally different quantized version.
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#118What'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?
Demis is on record saying they need models on the edge and if they’ll be there they might as well be properly open as they’ll be dumped anyway.
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#119What are the use cases for these small models? Is there anyone using models of this scale in their daily life who could share their experience?
This is one https://post.bot/
Re: Gemma 4 12B: A unified, encoder-free multimodal model
#120I 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 just fine.
So, with those qualifiers, I think it's a decent local coding model. It roughly compares with GPT-4.1 (!!), released 14 months ago, on the output: https://senko.net/vibecode-bench/2025/minesweeper-gpt-4.1.ht... (actually I'd call it better, but those syntax errors...)
I ran the quantized version (4-bit GGUF) on my consumer-grade card with 12G of VRAM and got 5t/s for output. Not for interactive use for coding, but fairly capable model.
To me, it's fascinating how much progress we got in over a year. GPT-4.1 was considered an extremely capable coding model. Now we got something with 12B of params performing roughly the same (in this specific benchmark, disclaimers, etc).
Lists of various models I tested: https://senko.net/vibecode-bench/