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

Google releases Gemma 4 open models

deepmind.google

Post reply on HN
Print view View original

61–70 of 507 posts

Re: Google releases Gemma 4 open models

#61

Post by azinman2 »

antirez wrote: post #10

Featuring the ELO score as the main benchmark in chart is very misleading. The big dense Gemma 4 model does not seem to reach Qwen 3.5 27B dense model in most benchmarks. This is obviously what matters. The small 2B / 4B models are interesting and may potentially be better ASR models than specialized ones (not just for performances but since they are going to be easily served via llama.cpp / MLX and front-ends). Also…

I find the benchmarks to be suggestive but not necessarily representative of reality. It's really best if you have your own use case and can benchmark the models yourself. I've found the results to be surprising and not what these public benchmarks would have you believe.

Re: Google releases Gemma 4 open models

#62

Post by WarmWash »

chasd00 wrote: post #33
wg0 wrote: post #18

Google might not have the best coding models (yet) but they seem to have the most intelligent and knowledgeable models of all especially Gemini 3.1 Pro is something. One more thing about Google is that they have everything that others do not: 1. Huge data, audio, video, geospatial 2. Tons of expertise. Attention all you need was born there. 3. Libraries that they wrote. 4. Their own data centers and cloud. 4. Most of…

Not sure why you're being downvoted, the other thing Google has is Google. They just have to spend the effort/resources to keep up and wait for everyone else to go bankrupt. At the end of the day I think Google will be the eventual LLM winner. I think this is why Meta isn't really in the race and just releases open weight models, the writing is on the wall. Also, probably why Apple went ahead and signed a deal with G…

The rumor is also that Meta is looking to lease Gemini similar to Apple, as their recent efforts reportedly came up short of expectations.

Re: Google releases Gemma 4 open models

#63

Post by vunderba »

kejaed wrote: post #42
vunderba wrote: post #34

Earlier quoted context omitted.

Not OP but one example is that recent VL models are more than sufficient for analyzing your local photo albums/images for creating metadata / descriptions / captions to help better organize your library.

Any pointers on some local VLMs to start with?

The easiest way to get started is probably to use something like Ollama and use the `qwen3-vl:8b` 4‑bit quantized model [1].

It's a good balance between accuracy and memory, though in my experience, it's slower than older model architectures such as Llava. Just be aware Qwen-VL tends to be a bit verbose [2], and you can’t really control that reliably with token limits - it'll just cut off abruptly. You can ask it to be more concise but it can be hit or miss.

What I often end up doing and I admit it's a bit ridiculous is letting Qwen-VL generate its full detailed output, and then passing that to a different LLM to summarize.

- [1] https://ollama.com/library/qwen3-vl:8b

- [2] https://mordenstar.com/other/vlm-xkcd

Re: Google releases Gemma 4 open models

#65

Post by regularfry »

minimaxir wrote: post #6

The benchmark comparisons to Gemma 3 27B on Hugging Face are interesting: The Gemma 4 E4B variant ( https://huggingface.co/google/gemma-4-E4B-it ) beats the old 27B in every benchmark at a fraction of parameters. The E2B/E4B models also support voice input, which is rare.

Thinking vs non-thinking. There'll be a token cost there. But still fairly remarkable!

Re: Google releases Gemma 4 open models

#66

Post by azinman2 »

canyon289 wrote: post #51

Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can

How do the smaller models differ from what you guys will ultimately ship on Pixel phones?

What's the business case for releasing Gemma and not just focusing on Gemini + cloud only?

Re: Google releases Gemma 4 open models

#67

Post by chrislattner »

If you want the fastest open source implementation on Blackwell and AMD MI355, check out Modular's MAX nightly. You can pip install it super fast, check it out here: https://www.modular.com/blog/day-zero-launch-fastest-perform...

-Chris Lattner (yes, affiliated with Modular :-)

Re: Google releases Gemma 4 open models

#68

Post by abhikul0 »

canyon289 wrote: post #51

Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can

Thanks for this release! Any reason why 12B variant was skipped this time? Was looking forward for a competitor to Qwen3.5 9B as it allows for a good agentic flow without taking up a whole lotta vram. I guess E4B is taking its place.

Re: Google releases Gemma 4 open models

#69

Post by regularfry »

xfalcox wrote: post #30
bertili wrote: post #25

Qwen: Hold my beer https://news.ycombinator.com/item?id=47615002

Comparing a model you can downloads weights for with an API-only model doesn't make much sense.

My money's on whatever models qwen does release edging ahead. Probably not by much, but I reckon they'll be better coders just because that's where qwen's edge over gemma has always been. Plus after having seen this land they'll probably tack on a couple of epochs just to be sure.

Re: Google releases Gemma 4 open models

#70

Post by mohsen1 »

canyon289 wrote: post #51

Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can

On LM Studio I'm only seeing models/google/gemma-4-26b-a4b

Where can I download the full model? I have 128GB Mac Studio

Post reply on HN