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 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6

Gemma 4 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6

10
Comments 3
13 min read
Use Local LLM to Enable AI Enhancement for Speech-to-Text Dictation

Use Local LLM to Enable AI Enhancement for Speech-to-Text Dictation

Comments
5 min read
Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16

Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16

2
Comments
9 min read
Why I Chose Gemma 4 E2B for Subra AI: The Reality of Running LLMs on Mid-Range Phones

Why I Chose Gemma 4 E2B for Subra AI: The Reality of Running LLMs on Mid-Range Phones

1
Comments
3 min read
The hardest part of a long-running agent job is knowing where it got to

The hardest part of a long-running agent job is knowing where it got to

Comments
5 min read
2B Gemma 4 Deployment with Cloud Run, NVIDIA L4, MCP SDK 2.x, and Claude Code

2B Gemma 4 Deployment with Cloud Run, NVIDIA L4, MCP SDK 2.x, and Claude Code

8
Comments 1
13 min read
I Used GPT-6 Astra, Claude Fable 5.1, and Gemini 3.8 Flash — Is Paying 13 More Actually Worth It?

I Used GPT-6 Astra, Claude Fable 5.1, and Gemini 3.8 Flash — Is Paying 13 More Actually Worth It?