ALERT!
Click here to register with a few steps and explore all our cool stuff we have to offer!
The Lounge

Google dropped Gemma 4 and nobody is talking about it

Submitted by CheapAI at 04-04-2026, 03:46 AM


Google dropped Gemma 4 and nobody is talking about it
635 Views
CheapAI's Avatar'
CheapAI
Offline
#1
aight so google quietly released gemma 4 yesterday and idk why this isnt blowing up more because this shit is actually insane
first thing – the license. previous gemma models were kinda ass because of weird restrictions, you couldnt really do anything commercial with them. now its apache 2.0. finally. use it, fine-tune it, sell it, do whatever. google took long enough lol
the models:
theres 4 of them. two "big" ones for workstations and two tiny ones for edge devices
the big ones:
  • 26B MoE – sounds big but only 3.8B parameters are active at once. so basically 27B quality at 4B compute cost. thats actually clever ngl
  • 31B dense – 256K context, vision built in, handles different image aspect ratios natively
the small ones (E2B and E4B) are the ones that got me tho. these things run on a T4 GPU (basically nothing) and still have vision, audio, function calling AND thinking mode. on an edge model. thats kinda wild
whats actually good:
  • multimodal is NATIVE not bolted on like with some other models
  • thinking mode you can toggle on and off depending on if you need it
  • 140 languages pretrained, real time translation works surprisingly well
  • audio encoder got compressed hard – from 681M down to 305M params, way faster response times
my opinion:
honestly if youve been ignoring gemma because of the old license drama this is worth a second look. its not gonna beat gpt-5 or claude 4 on everything but for local/self-hosted use cases its probably the best option rn. the MoE architecture is smart and the edge models are genuinely impressive for the size
only thing i dont love is google cloud pricing if you want to run the big version serverless but whatever you can selfhost
grab it on huggingface: https://huggingface.co/collections/google/gemma-4

if you want api access to this and other models without running your own hardware check https://cheap-api.shop – no subscription just pay per use
more stuff like this in the discord: https://discord.gg/fxmgdwDvbH
0
Reply



Users browsing this thread: 1 Guest(s)