DEV Community

Gemma

Gemma is a collection of lightweight, state-of-the-art open models built from the same technology that powers our Gemini models.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't
xbill profile

Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't

#gemma #jax #googleai #machinelearning
1
6 min read
Giving the AI Assisted Job Search a Local Brain
subraatakumar profile

Giving the AI Assisted Job Search a Local Brain

#ai #webdev #gemma
6 min read
Go Completely Offline: Build a Privacy-First Personal Finance Assistant with LiteRT and Gemma 4 [GDE]
railsstudent profile

Go Completely Offline: Build a Privacy-First Personal Finance Assistant with LiteRT and Gemma 4 [GDE]

#gemma #angular #tutorial #ai
2
7 min read
Go Completely Offline: Build a Privacy-First Personal Finance Assistant with LiteRT and Gemma 4
railsstudent profile

Go Completely Offline: Build a Privacy-First Personal Finance Assistant with LiteRT and Gemma 4

#gemma #ai #angular #webdev
5
7 min read
LM Studio on Windows, WSL2 for Development: The Setup Guide I Wish I Had
acel profile
Acel

LM Studio on Windows, WSL2 for Development: The Setup Guide I Wish I Had

#gemma #lmstudio #wsl #python
7 min read
Building a self-healing scraper agent that won't ship a fix it can't prove
athoughtfulsoul profile

Building a self-healing scraper agent that won't ship a fix it can't prove

#gemini #gemma #ai
5 min read
Benchmarking Gemini 2.5 Flash vs 3.1 Flash-Lite vs Gemma 4 with LLM judge (Claude Fable 5)
io_56a2cd4aff31d profile

Benchmarking Gemini 2.5 Flash vs 3.1 Flash-Lite vs Gemma 4 with LLM judge (Claude Fable 5)

#ai #gemini #gemma #claude
3 min read
Running Gemma 4 26B on a 13-Year-Old Xeon: Practical AI Performance Without GPUs
tamizuddin profile

Running Gemma 4 26B on a 13-Year-Old Xeon: Practical AI Performance Without GPUs

#ai #machinelearning #running #gemma
1
2 min read
How I Built Chat2Site: Zero-Code Web Generation Powered by Google’s Gemma 🚀
timothy_kelvin_3179694f25 profile

How I Built Chat2Site: Zero-Code Web Generation Powered by Google’s Gemma 🚀

#gemma #googlecloud #webdev #ai
1
3 min read
Latency vs. Tokens: What I Learned Optimizing an Agent with Gemma (and What Didn't Work)
leslysandra profile

Latency vs. Tokens: What I Learned Optimizing an Agent with Gemma (and What Didn't Work)

#gemma #genai #experiment #education
15
4
6 min read
Agentic farm advisory assistant built with Gemma 4 + Google AI Studio
shieldstring profile

Agentic farm advisory assistant built with Gemma 4 + Google AI Studio

#ai #machinelearning #gemma #javascript
1
6 min read
plot twist: i actually won a gemma 4 hackathon this time
ayushh0110 profile

plot twist: i actually won a gemma 4 hackathon this time

#gemma #ai #productivity #machinelearning
2
2 min read
Serving Gemma 4 2B on a Single TPU v5e Chip with MCP and Antigravity CLI
xbill profile

Serving Gemma 4 2B on a Single TPU v5e Chip with MCP and Antigravity CLI

#antigravitycli #python #mcps #gemma
10
17 min read
How I Built a Premium Developer Tools Website Using Only a Local LLM (Gemma 4:12B + Ollama + VS Code)
iprvn profile

How I Built a Premium Developer Tools Website Using Only a Local LLM (Gemma 4:12B + Ollama + VS Code)

#showdev #gemma #webdev #productivity
5 min read
MLOps for LLM: A Case Study on Dresscode
saad4software profile

MLOps for LLM: A Case Study on Dresscode

#mlops #llm #gemma #ai
21 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.