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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Deploying Gemma 12B to AWS EC2 with NVIDIA L4 and Antigravity CLI

Deploying Gemma 12B to AWS EC2 with NVIDIA L4 and Antigravity CLI

7
Comments
23 min read
Deploying Gemma 12B to AWS EC2 with NVIDIA L4

Deploying Gemma 12B to AWS EC2 with NVIDIA L4

Comments
23 min read
caveman 真的能幫我省下 Token 帳單嗎?

caveman 真的能幫我省下 Token 帳單嗎?

Comments
2 min read
My Bookmark Engine Returned Chunks. I Added One Endpoint to Make It Answer.

My Bookmark Engine Returned Chunks. I Added One Endpoint to Make It Answer.

11
Comments 2
3 min read
Turning Gemma 4 into an Old Korean Translator

Bridging the gap for modern native speakers

Turning Gemma 4 into an Old Korean Translator

29
Comments 2
4 min read
What Actually Runs Well on a GTX 1080 Ti in 2026 (Measured)

What Actually Runs Well on a GTX 1080 Ti in 2026 (Measured)

Comments
3 min read
Gemma 4 QAT on a 1080 Ti: What 'Quantization-Aware' Actually Buys — and Fitting the 12B on 8 GB at 16k

Gemma 4 QAT on a 1080 Ti: What 'Quantization-Aware' Actually Buys — and Fitting the 12B on 8 GB at 16k

Comments
5 min read
MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

1
Comments
3 min read
Project Log #2: The AI Phone Agent Has a Repo

Project Log #2: The AI Phone Agent Has a Repo

Comments
1 min read
Comparing Model Performance: Without MTP vs. With MTP vs. With MTP + QAT

Comparing Model Performance: Without MTP vs. With MTP vs. With MTP + QAT

Comments
8 min read
Deployment Planning with Gemma 26B, NVIDIA L4, MCP, Cloud Run, and Antigravity CLI

Deployment Planning with Gemma 26B, NVIDIA L4, MCP, Cloud Run, and Antigravity CLI

6
Comments
23 min read
Project Log #1: I'm Building an AI Agent That Controls a Phone

Project Log #1: I'm Building an AI Agent That Controls a Phone

Comments
2 min read
Gemma 4 makes on-device multimodal AI good enough to ship

Gemma 4 makes on-device multimodal AI good enough to ship

Comments
4 min read
Connecting RooCode to Gemma4-26B-MoE via OpenAI Bridge

Connecting RooCode to Gemma4-26B-MoE via OpenAI Bridge

5
Comments
2 min read
Building the Future of Local AI Intelligence

Gemma 4 Challenge: Write about Gemma 4 Submission

Building the Future of Local AI Intelligence

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.