Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't
This article is about running a hand-written Gemma 4 port in pure JAX on three different accelerators, and about the two places the abstraction leak…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Go Completely Offline: Build a Privacy-First Personal Finance Assistant with LiteRT and Gemma 4
Imagine having a personal financial planner that analyzes your sensitive transaction history, flags spending anomalies, and suggests budget optimiza…
Building a self-healing scraper agent that won't ship a fix it can't prove
I built patchwright for Google's All Things Agentic Hackathon, and this post is my write-up of it, written for the purpose of entering. The short ve…
Serving Gemma 4 2B on a Single TPU v5e Chip with MCP and Antigravity CLI
This article is the v5e follow-on to the v6e-1 debugging guide . Same MCP tooling, same Antigravity CLI driver, smaller and cheaper silicon — and a…
Smash Stories: The Bug That Whispered for Two Weeks Before I Heard It
This is a submission for DEV's Summer Bug Smash: Smash Stories powered by Sentry . My AI agent was misreading financial data 1 in 5 times. No crashe…
Benchmarking Gemini 2.5 Flash vs 3.1 Flash-Lite vs Gemma 4 with LLM judge (Claude Fable 5)
Cross-posted from the IO reader blog , where the full version includes all 36 unedited transcripts side by side. With gemini-2.5-flash scheduled to…
Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me
I ported the whole Gemma-4 family — E2B, E4B, 12B, 31B, and the 26B-A4B MoE — to run on AWS Inferentia2. Each has its own write-up in this series; t…
Running Gemma 4 26B on a 13-Year-Old Xeon: Practical AI Performance Without GPUs
Originally published on tamiz.pro . Introduction Large language models like Gemma 4 26B typically require powerful GPUs with high VRAM. This tutoria…
DiffusionGemma: 4x faster text generation
Our newest open experimental model delivers up to 4x faster inference on dedicated GPUs and opens the door to exploring speed-critical, interactive…
Save yourself from drowning
Dev.to is an absolute goldmine. On any given day, thousands of builders are sharing brilliant engineering lessons, launching side projects, breaking…
Master Local Fine-Tuning with "gemma-trainer"
Remember back in May when I introduced the gemma-skills repository? It's been rewarding to see how many of you have used my previous post to streaml…
Gemma, the Epstein Files, and sandboxing cause a stir at the World's Fair
As the AI Engineer World’s Fair kicked off officially on Monday, the halls were filled for the traditional workshop day, where coders from across th…
How I Built a Premium Developer Tools Website Using Only a Local LLM (Gemma 4:12B + Ollama + VS Code)
Over the past few weeks, I’ve been experimenting with local language models. Like a lot of developers, I’ve used cloud AI assistants quite a bit, bu…
MLOps for LLM: A Case Study on Dresscode
I've recently participated in the Gemma 4 challenge here on DEV.to, but fell short compared to many amazing projects. I really liked LIKAS . I encou…
Solstice Eternal – AI Powered Adventure Game with Gemma 4
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Solstice Eternal – AI Adventure Game Solstice Eternal is an interact…
MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent
In my MTP post , speculative decoding roughly doubled Qwen3.6-27B generation on a 3090. It's tempting to read that as "turn on MTP, go faster." So I…
No Cloud, No Cost: Build an Offline Visual AI Agent with Gemma 4
With Google’s Gemma 4 12B , you can host a highly intelligent assistant that natively understands text and images right on your everyday laptop. Bec…
Project Log #1: I'm Building an AI Agent That Controls a Phone
I'm starting a new project. It's the most ambitious thing I've attempted from a phone. The goal: an AI agent that controls a smartphone. It opens ap…
Connecting RooCode to Gemma4-26B-MoE via OpenAI Bridge
This configuration bypasses extension UI limitations by routing direct Google AI Studio requests through Google’s native OpenAI-compliant endpoint.…
Breathing Life into the Pi: Deploying Gemma 4 2B on a Raspberry Pi 5
Hi Everyone, I’m back with a brand new project, and this one has been a long time coming. For a while now, I’ve had this persistent urge to build my…
Structure: A Local-First Interview IDE Powered by Gemma 4
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Structure is a local-first macOS desktop IDE for technical interview…
I Generated a Tableau Dashboard Using Gemma 4 — Locally, No API Key, No Cloud
Why I Wanted to Try This With Gemma 4 I’ve been building Twilize — a tool that generates Tableau workbooks from natural language — for a while now.…
Quantizing Gemma 4 on Mac with llama.cpp
requirements hugging face account https://huggingface.co/ Setup llama.cpp git clone https://github.com/ggml-org/llama.cpp.git cmake -S llama.cpp -B…
Adding Gemma 4 speech recognition to a .NET desktop app: the llama-server sidecar that survived
In April 2026 Google shipped Gemma 4, a multimodal model with a native audio path. I wanted to add it to Parlotype, my .NET 10 dictation app, as a s…
Your To-Do List Doesn't Know You — So I Gave Mine Three Brains
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Architecture: graph TD subgraph Client["CLIENT LAYER"] FL["Flutter a…
Using Gemma4 2B to Assist Community Health Workers
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Problem Statement Nigeria has a scarcity of health workers, with the ratio of do…
Everbench: A document management system with Local Intelligence
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Everbench Everbench is a low-cost, efficient document research platf…
Gemma 4 Made Me Rethink Local AI: Not Just Text, But Images Too
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Most people (including me, initially) think of "local AI" as a text‑only chatbot…
🛡️ PromptGuard: I Built a Local AI Privacy Firewall That Sanitizes Your Prompts Before They Leave Your Machine
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 Every time you paste sensitive data, legal documents, or personal details into Ch…
Gemma 4: The 128K Multimodal Powerhouse in Your Terminal
A raw, developer-first look at Google’s new open-weight Gemma 4 family—featuring a hands-on local Python setup, a comparison of the 2B, 9B, and 31B…