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.
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
14
Comments 2
6 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
9
Comments
17 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
1
Comments
2 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
Comments
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
Comments
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
Comments
3 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
Comments
6 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
Comments
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
Comments
21 min read
DiffusionGemma: 4x faster text generation
geminiteam profile

DiffusionGemma: 4x faster text generation

#gemma #google #llm #ai
18
Comments
5 min read
I built a landing page with Three.js, vanilla JS, and zero frameworks — here's what I learned
ayushh0110 profile

I built a landing page with Three.js, vanilla JS, and zero frameworks — here's what I learned

#webdev #productivity #opensou #gemma
2
Comments
4 min read
Running Gemma 4 On-Device on Android: Building a Private AI Assistant with LiteRT
sai888 profile

Running Gemma 4 On-Device on Android: Building a Private AI Assistant with LiteRT

#android #gemma #ondeviceai #litert
Comments
4 min read
Ask me anything (RAG)

Gemma 4 Challenge: Build With Gemma 4 Submission
ifeanyichima profile

Ask me anything (RAG)

#devchallenge #gemmachallenge #gemma #ai
3
Comments
2 min read
Debugging Deployments with Gemma 4B, TPU v6e-1, MCP, and Antigravity CLI
xbill profile

Debugging Deployments with Gemma 4B, TPU v6e-1, MCP, and Antigravity CLI

#antigravitycli #python #mcps #gemma
6
Comments 1
20 min read
Debugging Deployments with Gemma 12B, TPU v6e-4, MCP, and Antigravity CLI
xbill profile

Debugging Deployments with Gemma 12B, TPU v6e-4, MCP, and Antigravity CLI

#mcps #gemma #tpu #benchmark
5
Comments
16 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.