DEV Community

xbill profile picture

xbill

Master of MCP and herding cats

DEV Weekend Challenge Completion
2
Frontend Challenge Completion Badge
One Year Club
Cloud Run Badge
Go
June Solstice Game Jam Completion
Azure
GitHub Copilot "Finish-Up-A-Thon" Challenge Completion
Gemma 4 Challenge Completion
Hermes Agent Challenge Completion
Google I/O 2026 Writing Challenge Completion
4 Week Community Wellness Streak
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

1
Comments
9 min read

Want to connect with xbill?

Create an account to connect with xbill. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
It's Got What Content Craves: Sanity, Built for the People of Idiocracy

Sanity Challenge Path Two Submission

It's Got What Content Craves: Sanity, Built for the People of Idiocracy

Comments
9 min read
Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys

Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys

11
Comments 5
9 min read
An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

12
Comments 5
20 min read
A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4

A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4

15
Comments 6
6 min read
Four Iceberg Tools, Three Agent Frameworks: What Ports, and What Doesn't

Four Iceberg Tools, Three Agent Frameworks: What Ports, and What Doesn't

7
Comments 1
18 min read
Four Iceberg Tools, Three Agent Frameworks: What Ports, and What Doesn't

Four Iceberg Tools, Three Agent Frameworks: What Ports, and What Doesn't

Comments
18 min read
Nano Banana 2 Lite in Kiro CLI 3: MCP 2.0, the New Interactions API, and Headless Permissions

Nano Banana 2 Lite in Kiro CLI 3: MCP 2.0, the New Interactions API, and Headless Permissions

2
Comments
12 min read
Nano Banana 2 Lite in Kiro CLI 3: MCP 2.0, the New Interactions API, and Headless Permissions

Nano Banana 2 Lite in Kiro CLI 3: MCP 2.0, the New Interactions API, and Headless Permissions

8
Comments
12 min read
Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4

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

9
Comments 1
16 min read
Nano Banana 2 Lite, Revisited: MCP 2.0, the New Interactions API, and Three Agent CLIs

Nano Banana 2 Lite, Revisited: MCP 2.0, the New Interactions API, and Three Agent CLIs

10
Comments 1
12 min read
Two Rust Clients for Gemma 4: Calling the Endpoint vs. Calling the MCP Server 🦀

Two Rust Clients for Gemma 4: Calling the Endpoint vs. Calling the MCP Server 🦀

8
Comments 1
17 min read
FastMCP Is Now MCPServer on AWS: Moving a boto3 EC2 MCP Server to the MCP Python SDK 2.x

FastMCP Is Now MCPServer on AWS: Moving a boto3 EC2 MCP Server to the MCP Python SDK 2.x

Comments 1
9 min read
FastMCP Is Now MCPServer: Migrating a Python MCP Server to the MCP SDK 2.x

Dependency upgrades break shared environments

FastMCP Is Now MCPServer: Migrating a Python MCP Server to the MCP SDK 2.x

13
Comments 10
12 min read
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
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
Four Debian 13 Boxes, One Brief: 1,923 Packages on Metal, 328 in the Cloud

Four Debian 13 Boxes, One Brief: 1,923 Packages on Metal, 328 in the Cloud

1
Comments 3
11 min read
Four Debian 13 Boxes, One Brief: 1,923 Packages on Metal, 328 in the Cloud

Four Debian 13 Boxes, One Brief: 1,923 Packages on Metal, 328 in the Cloud

10
Comments 2
11 min read
The Desktop Looked Right: 2,093 Parse Errors a Boot, and 10.9 Seconds That Weren't Doing Anything

The Desktop Looked Right: 2,093 Parse Errors a Boot, and 10.9 Seconds That Weren't Doing Anything

3
Comments 1
16 min read
The Cable Buys Headroom: 91% of a USB 2.0 Bus, 3.6% of a Thunderbolt One

The Cable Buys Headroom: 91% of a USB 2.0 Bus, 3.6% of a Thunderbolt One

12
Comments 1
18 min read
Generosity Is a Default Setting

DEV Weekend Challenge: Generosity Edition Submission 💜

Generosity Is a Default Setting

2
Comments 2
9 min read
AWS Has Two Iceberg REST Catalogs: What Each One Actually Serves

AWS Has Two Iceberg REST Catalogs: What Each One Actually Serves

Comments 1
8 min read
Seven Iceberg REST Catalogs: What They Declare, and What They Serve

Seven Iceberg REST Catalogs: What They Declare, and What They Serve

7
Comments 4
17 min read
ChromeOS Lookalikes, Two Ways: One With Drivers, One Without

ChromeOS Lookalikes, Two Ways: One With Drivers, One Without

8
Comments 2
8 min read
Three Gemma 4 Deployments on One T4G for Under $3: What the Runtime Changes, and What It Doesn't

Three Gemma 4 Deployments on One T4G for Under $3: What the Runtime Changes, and What It Doesn't

Comments 2
14 min read
Three Gemma 4 Deployments on One T4G for Under $3: What the Runtime Changes, and What It Doesn't

Three Gemma 4 Deployments on One T4G for Under $3: What the Runtime Changes, and What It Doesn't

8
Comments 4
14 min read
Streamline Publishing with a Claude Code Skill

Streamline Publishing with a Claude Code Skill

Comments 1
7 min read
Streamline Publishing with a Claude Code Skill

Streamline Publishing with a Claude Code Skill

18
Comments 4
7 min read
g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput

g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput

5
Comments 2
6 min read
Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't

Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't

3
Comments
8 min read
The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One

The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One

3
Comments
11 min read
Gemma 4 in Pure JAX: What Ports from TPU to GPU, and What Doesn't

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

8
Comments 3
6 min read
Pure JAX on G5g: Serving Gemma 4 on Graviton and a T4G

Pure JAX on G5g: Serving Gemma 4 on Graviton and a T4G

Comments
8 min read
Cross Cloud A2A Agent Card Field Comparison

Cross Cloud A2A Agent Card Field Comparison

7
Comments
20 min read
What Bedrock AgentCore Actually Puts on Your A2A Agent Card

What Bedrock AgentCore Actually Puts on Your A2A Agent Card

Comments 1
9 min read
Mix and Match: One Agent, Three Clouds, One Protocol

Mix and Match: One Agent, Three Clouds, One Protocol

10
Comments 1
16 min read
Mix and Match: Serving an ADK Agent to AWS and Azure

Mix and Match: Serving an ADK Agent to AWS and Azure

8
Comments
10 min read
Mix and Match: Serving a Bedrock Agent to Google and Azure

Mix and Match: Serving a Bedrock Agent to Google and Azure

Comments 1
11 min read
Three Clouds, One Brief: What Actually Differs Between ADK, Strands and Agent Framework

Three Clouds, One Brief: What Actually Differs Between ADK, Strands and Agent Framework

8
Comments
16 min read
Strands on AgentCore, Answering Two Other Clouds: The Contract, the Header, and the microVM

Strands on AgentCore, Answering Two Other Clouds: The Contract, the Header, and the microVM

Comments
9 min read
ADK Beyond Its Own Tests: What Happens When Your Agent Answers a Client That Is Not ADK

ADK Beyond Its Own Tests: What Happens When Your Agent Answers a Client That Is Not ADK

7
Comments
9 min read
Deploying a QAT Checkpoint Your Serving Stack Can't Load: Gemma 4 E2B in Pure JAX on One TPU

Deploying a QAT Checkpoint Your Serving Stack Can't Load: Gemma 4 E2B in Pure JAX on One TPU

8
Comments
10 min read
Build an MCP server in Rust with rmcp: a walk-through 🦀

Build an MCP server in Rust with rmcp: a walk-through 🦀

10
Comments
9 min read
Build an MCP server in Rust with rmcp: a walk-through 🦀

Build an MCP server in Rust with rmcp: a walk-through 🦀

3
Comments 1
9 min read
Shipping a vision-model verdict on Bedrock and Lightsail

Shipping a vision-model verdict on Bedrock and Lightsail

1
Comments 1
9 min read
I built a security scanner that checks if you are a dog

DEV Weekend Challenge: Dog Days Edition Submission 🐕

I built a security scanner that checks if you are a dog

14
Comments 4
9 min read
Serving Gemma4 with Rust on vLLM 🦀

Serving Gemma4 with Rust on vLLM 🦀

10
Comments
10 min read
Installing Rust for vLLM on Graviton: a G5g walk-through 🦀

Installing Rust for vLLM on Graviton: a G5g walk-through 🦀

Comments
10 min read
Building and Serving vLLM with Rust

Building and Serving vLLM with Rust

Comments
9 min read
Looker's Native MCP Server with Claude Code

Looker's Native MCP Server with Claude Code

11
Comments
9 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

Comments
9 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

13
Comments
9 min read
Do I Still Need a Monkey Patch for Gemini Live?

Do I Still Need a Monkey Patch for Gemini Live?

11
Comments 2
11 min read
MCP Configuration for Looker with Codex

MCP Configuration for Looker with Codex

17
Comments 2
24 min read
Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't

Serving Gemma 4 E2B on a TPU v6e-1: what Trillium buys, and what it doesn't

2
Comments
20 min read
Three Clouds, Three Native Agents

Three Clouds, Three Native Agents

10
Comments 4
10 min read
Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1

Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1

16
Comments 1
21 min read
Build a Dart ADK Agent and MCP Server

Brings agents to Dart via SSE and Shelf

Build a Dart ADK Agent and MCP Server

22
Comments 24
4 min read
Serving Gemma 4 2B on a Single TPU v5e Chip with MCP and Antigravity CLI

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

10
Comments
17 min read
MCP Development Updates with Rust and Claude Code

MCP Development Updates with Rust and Claude Code

Comments
10 min read
loading...