
From 2B to 31B: The Evolution of Google's Gemma Models
A deep dive into the architectural shifts, parameter sizes, and deployment challenges of the DeepMind Gemma family from V1 to V4.
Hey, I'm Kukil. This is my journal - a running log of the things I'm building, breaking, and occasionally understanding.
If you like watching someone figure things out in real time, stick around. New posts whenever something interestingexplodes(literally or figuratively).
AI/ML
Robotics
Microcontrollers
Automation
3D Printing

OpenCV 5.0 rewrites the DNN engine, pushes ONNX coverage past 80%, runs VLMs natively, and drops the C API. A developer's take on what's real, what's promising, and where the gaps still are.

Explore my latest thoughts and tutorials

A deep dive into the architectural shifts, parameter sizes, and deployment challenges of the DeepMind Gemma family from V1 to V4.

A practical catalog of small language and vision models optimized for edge inference.

LiquidAI's LFMs use a hybrid convolution+attention architecture to deliver faster inference and lower memory than pure transformers. Full model catalog, tier-by-tier benchmarks, and ecosystem trade-offs.

A complete guide to the OpenBMB model ecosystem, including MiniCPM, Eurus, and their edge-computing efficiency.

Ditch the SD card shuffle. Build a unified Gradio web dashboard that connects to your Ender 3 V2 Neo via USB, fetches G-code files from the printer's SD card, and runs real-time YOLOv26 print failure detection.

You've built it, Now deploy it. From Cloudflared tunnels to production hardening, this post ties the entire self-hosted AI ecosystem together. Serving engines, chat interface, and code completion.
Hi! I'm a passionate developer exploring the intersections of AI/ML, Robotics, Microcontrollers, and Automation.
Through this blog, I share my learnings, experiments, and best practices in these exciting fields.
Read More About Me
Hover over each icon to see the magic of technology come to life
Get notified when I publish new blog posts and tutorials