Gemma

Explore recommended reads, summarized by AI

Technical Implementation

Guides and tutorials for deploying, fine-tuning, and building applications with Gemma models.

Fine-Tuning and Application Development

Local and Cloud Deployment

Popular this week

Google Cloud - Community

xbill

Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4

Sep 14

CodeStax.Ai

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

Oct 28

Towards AI

Srikanth Dongala

EmbeddingGemma 2: Multimodal Search for the Cost of a Text Model

Oct 8

Aditya Inamdar

Gemma 4 E4B: The 8GB VRAM Model That Finally Feels Like a Daily Driver

Sep 25

Google Cloud - Community

Robina Mirbahar

Building Production-Ready Open-Weights AI Agents with Gemma, Google ADK, and Cloud Run GPUs

Oct 21

Selected by Medium

AI Advances

Kennedy Selvadurai, PhD

A Personal Living Knowledge Base with Zed Agent and a Local LLM

May 23

Latest stories

Taiko Toeda

Scaffolding helps the smallest Gemma 4 agent, not the larger ones

5d ago

CodeStax.Ai

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

Oct 28

Google Cloud - Community

Amanda Fitch

Build a smart search bot for your phone

Oct 27

Google Cloud - Community

Ariel Jassan

Host Your Own System 1 Decision Model: Serving DiffusionGemma 26B on the Gemini Enterprise Agent…

Oct 22

Google Cloud - Community

Karl Weinmeister

When to use a diffusion LLM: I compared DiffusionGemma and Gemma 4

Oct 22

See more stories

Gemma

Technical Implementation

Fine-Tuning and Application Development

Local and Cloud Deployment

Popular this week

Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

EmbeddingGemma 2: Multimodal Search for the Cost of a Text Model

Gemma 4 E4B: The 8GB VRAM Model That Finally Feels Like a Daily Driver

Building Production-Ready Open-Weights AI Agents with Gemma, Google ADK, and Cloud Run GPUs

Selected by Medium

A Personal Living Knowledge Base with Zed Agent and a Local LLM

Latest stories

Scaffolding helps the smallest Gemma 4 agent, not the larger ones

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

Build a smart search bot for your phone

Host Your Own System 1 Decision Model: Serving DiffusionGemma 26B on the Gemini Enterprise Agent…

When to use a diffusion LLM: I compared DiffusionGemma and Gemma 4

Who to follow

Popular this week

Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

EmbeddingGemma 2: Multimodal Search for the Cost of a Text Model

Gemma 4 E4B: The 8GB VRAM Model That Finally Feels Like a Daily Driver

Building Production-Ready Open-Weights AI Agents with Gemma, Google ADK, and Cloud Run GPUs

Selected by Medium

A Personal Living Knowledge Base with Zed Agent and a Local LLM

Latest stories

Scaffolding helps the smallest Gemma 4 agent, not the larger ones

Why Google’s DiffusionGemma Is So Fast (And Where It Falls Short)

Build a smart search bot for your phone

Host Your Own System 1 Decision Model: Serving DiffusionGemma 26B on the Gemini Enterprise Agent…

When to use a diffusion LLM: I compared DiffusionGemma and Gemma 4

Who to follow