Gemma 3 Technical Report [pdf]
storage.googleapis.com
Gemma 3 Technical Report [pdf]
1–10 of 260 posts
Re: Gemma 3 Technical Report [pdf]
#2Gemma 3 is out! Multimodal (image + text), 128K context, supports 140+ languages, and comes in 1B, 4B, 12B, and 27B sizes with open weights & commercial use.
Gemma 3 model overview: https://ai.google.dev/gemma/docs/core
Huggingface collection: https://huggingface.co/collections/google/gemma-3-release-67...
Re: Gemma 3 Technical Report [pdf]
#3> We also change the architecture of
the model to reduce the KV-cache memory that tends to ex plo de with long context
This is key (pun not intended). It's one thing to run these models locally; it's a totally different game when you need longer context.
Sure, the new M3 Ultra can fit a Q4 DeepSeek r1 in URAM, but as soon as you wanna get usable context like +64k, the t/s and PP quickly become prohibitive.
Speaking of M3 Ultra, I really wish Apple had put more bandwidth in this beast of a machine. It's got a lot of "energy", not a lot of "power" to actually use that energy.
Re: Gemma 3 Technical Report [pdf]
#4Can someone explain Gemma vs Gemini for me please?
Re: Gemma 3 Technical Report [pdf]
#5Can someone explain Gemma vs Gemini for me please?
Gemma is their open-source series of models. Gemini is the propertierary ones. Gemini models are bigger and better. But Gemma are pretty good too.
Re: Gemma 3 Technical Report [pdf]
#6Super cool models! Love the mixture of sliding window and global attention to cut down on KV cache sizes! And 4B, 12B and 27B are vision + text by default! Super cool!
Re: Gemma 3 Technical Report [pdf]
#7Looks great! So excited about this! We have been using gemma models since gemma 1.0 and they are so far ahead of the curve!
Re: Gemma 3 Technical Report [pdf]
#8Someone knows whether there is support for multiple images as input ? I don't see it from the docs yet.
Re: Gemma 3 Technical Report [pdf]
#9doesn't seem to have hit the LMArena yet. will be interesting to see where it places there.
Re: Gemma 3 Technical Report [pdf]
#10Someone knows whether there is support for multiple images as input ? I don't see it from the docs yet.
Yes
> If you want to prompt with more than one image, you must include a tag for each image included in your prompt.
From here: https://github.com/google/generative-ai-docs/blob/78688755db...