Google's free Gemma 4 model runs on hardware you probably already own
… Related Google's Gemma 4 isn't the smartest local LLM I've run, but it's the one I reach for most Google's newest Gemma 4 models are both powerful and useful. …
Search
Tracked topic
Google Gemma
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
Top stories
I tested Gemma 4, Qwen 3.5, and Ministral 3 for vision tasks, and only one understood the assignment
4d agoI dumped 650K DNS records into Gemma, and it found patterns my dashboard completely missed
5d agoI replaced Google Home and Alexa+ with a local voice assistant after realizing cloud AI isn't worth the privacy trade-off
6d agoGemma 4's smallest model runs on 3GB of VRAM, and it's the one I actually reach for
1w agoI tested Google's new Gemma 4 12B on my 8GB GPU, and now I don't want to go back to smaller models
… Google's new Gemma 4 12B is a pretty clean example of that direction . It was built with laptops and dedicated GPUs in mind, the stuff regular people actually own, and Google's been pushing the architecture as the main reason for that. …
Google's Gemma 4 finally made me care about running local LLMs
… That said, Google finally launched a model that pulled me back in and it's actually worth running. Google launched four new open-source models You don't need a home lab to use these models A few weeks ago, Google launched its newest family of open-source AI models : Gemma 4. …
I ran a powerful local AI model on my laptop, and it didn’t feel like a compromise
… Gemma 4 12B is the solution Right-sized architecture The arrival of Google DeepMind’s Gemma 12B changes the scenario. …
I finally found an open-source local LLM that actually competes with cloud AI
… Related Google's Gemma 4 isn't the smartest local LLM I've run, but it's the one I reach for most Google's newest Gemma 4 models are both powerful and useful. Open models got better when I wasn't looking Gemma 4 E4B wasn't what I expected from a free, local model. …
I ran a full LLM on my phone with no internet, and it's more useful than I expected
… Gemma 4 has replaced cloud models for my everyday AI tasks The tasks that keep me coming back I might be a writer for publications that are always at the whims of Google, but I'm not going to lie to you and say I still Google every little question that pops into my head. …
I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead
… Gemma 4 is Google's open-weight family with four sizes - the E2B and E4B edge variants made for phones and laptops, plus the bigger 26B MoE and 31B dense models. …
I ran Gemma, Llama, and Qwen on my phone, and only one of them is worth the storage
… Gemma 4 E2B Starting with what I already knew Gemma 4 E2B is Google's edge-first model, designed from the start to actually run on a phone rather than being shrunk down from something bigger. …
I put Google's Gemma 4 on my homelab and Tailscale on my phone — and cancelled Claude Pro
… Then Google announced Gemma 4, and the reasons I'd left local AI behind began to fade. Not because it beats Claude Pro — it wasn’t even close — but because it replaced the part I was actually paying for. Gemma 4 e4b, a Docker container, and Tailscale on my phone — the subscription was gone. …
Google's Gemma 4 isn't the smartest local LLM I've run, but it's the one I reach for most
… Google's new Gemma 4 models don't eliminate that trade-off entirely, but it comes closer than anything else I've tried. What makes Gemma 4 different from previous open-weight releases is the sheer range of what Google shipped. …