#GEmma

A storage appliance that shipped before AVX2 existed now runs Google's Gemma 4 26B in my basement, no GPU. Here's how we got a modern MoE model onto a CPU older than the instructions its inference engine assumed were there.

Running Gemma 4 26B-A4B and Qwen3.6 35B-A3B locally with llama.cpp, MTP speculative decoding, multimodal support, and PI as a coding agent.

We’re releasing Gemma 4 quantization-aware training checkpoints, reducing memory requirements and improving on-device performance.

Google's Gemma 4 12B ditches vision encoders, scores 72% on LiveCodeBench, and runs on 16GB. Here's why researchers are swapping Qwen for it.

I pulled the just-released Gemma 4 12B and ran it on a GTX 1080 Ti. ~28 tok/s at Q4 on one card — but three things broke first, and Q8 (2 cards, 30% slower) fixed both the token glitches and a domain answer Q4 got confidently wrong.

An overview of Gemma 4 12B, a model designed to bring high-performance multimodal intelligence directly to your laptop.

In addition to Google AI Edge Gallery, the company also released the Gemma 4 12B model and the Google AI Edge Eloquent dictation app for the Mac.

I want to run an LLM on iPhone. But there are several runtimes and it's not obvious which to...

We’re taking a look at an oldie but goodie, our GEMMA hoop earrings. GEMMA jewelry! The bitty board fits perfectly in the center of a NeoPixel ring for flashy hoop earrings or a charming pendant.…

You can now access Gemma 4 models (26B and 31B) on Vercel's AI Gateway with no markup and no other provider accounts required.

From Dev Community: TSI Nexus: An Open-Source Digital Brain Powered by Local Gemma 4 26B and Context Graphs

From Dev Community: Coding in the Dark: How Local Gemma 4 Saved My Python Progress During Ukrainian Blackouts

Gemma 4: Google's Open-Weight AI That Actually Runs on Your Machine #ai #machinelearning...

This is a submission for the Gemma 4 Challenge: Write About Gemma 4 For years, we built AI systems...

From Dev.to - opensource: PhotoLens — A Fully Offline, On-Device Photo Gallery That Gives Blind and Low-Vision Users Independent Access to Their Own Memories

If you've been watching the open-source LLM space, you've probably noticed it's been a great couple...

An honest 4-model comparison on one month of real trading bot logs. And what happens when you wrap Gemma 4 in a self-validation loop.

@jess @ben Just days ago, Google DeepMind launched Gemma 4, a family of open models that signals a...