▶ Videos →

📰 Dev.to · Rob

11 articles · Updated every 3 hours · View all reads

All Articles 169,322 Blog Posts 161,025 Tech Tutorials 45,010 Research Papers 33,041 News 21,566 ⚡ AI Lessons

Model Showdown Round 9: Qwen 3.6 27B vs Qwen 3.6 35B-A3B vs Qwythos-9B vs GLM-4.7-Flash vs Nemotron-3-Nano

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Model Showdown Round 9: Qwen 3.6 27B vs Qwen 3.6 35B-A3B vs Qwythos-9B vs GLM-4.7-Flash vs Nemotron-3-Nano

I put Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwythos-9B, GLM-4.7-Flash, and Nemotron-3-Nano through the same real coding task on my homelab RTX 5090. Along the way I h

TurboQuant, Four Months Later: Chasing Google's 6x VRAM Claim Into the Wild

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 1mo ago

TurboQuant, Four Months Later: Chasing Google's 6x VRAM Claim Into the Wild

Back in Q1 I read a headline about Google cutting AI memory use 6x and filed it under "watch and revisit." Four months later, Google still hasn't shipped offici

Can You Tell When an LLM API Swaps in a Cheaper Model?

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 2mo ago

Can You Tell When an LLM API Swaps in a Cheaper Model?

Providers have every reason to serve a smaller or more quantized model under load. I ran the experiment to see if you can catch it from the outside. The obvious

Frontier Bakeoff: We Benchmarked Fable 5 Hours Before the Shutdown

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 2mo ago

Frontier Bakeoff: We Benchmarked Fable 5 Hours Before the Shutdown

Four frontier models, ten tasks, one government shutdown. We ran Claude Fable 5 through the homelab benchmark harness three hours before Anthropic pulled the pl

Friday Fixes: Housekeeping the Homelab and Hub

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 2mo ago

Friday Fixes: Housekeeping the Homelab and Hub

A model refresh on the homelab (Qwen 3.6, new embeddings, 469 llama.cpp builds), a feature sprint on the vacation planning site (calendar sync, expense tracking

Thursday Thoughts: The Models We Can't Run

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

Thursday Thoughts: The Models We Can't Run

Every week or two, a model drops that makes the local AI community lose its collective mind. This...

The Agentic Gap: Claude Oneshots, Gemma Fails

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

The Agentic Gap: Claude Oneshots, Gemma Fails

Two days ago, Gemma 4 topped our local model benchmark — 167 tokens per second, perfect code quality...

Model Showdown: Benchmarking Local vs Cloud LLMs on a Real Coding Task

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

Model Showdown: Benchmarking Local vs Cloud LLMs on a Real Coding Task

Last post we stood up Ollama on the RTX 5090, pulled a stack of models, and wired them into our...

Putting the GPU to Work: Running Local LLMs on a Home Lab

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

Putting the GPU to Work: Running Local LLMs on a Home Lab

Yesterday we went from a gaming PC on a shelf to a fully configured Coder server with GitHub...

Putting the GPU to Work: Running Local LLMs on a Home Lab

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

Putting the GPU to Work: Running Local LLMs on a Home Lab

Yesterday we went from a gaming PC on a shelf to a fully configured Coder server with GitHub...

Model Showdown: Benchmarking Local vs Cloud LLMs on a Real Coding Task

Dev.to · Rob 🧠 Large Language Models ⚡ AI Lesson 3mo ago

Model Showdown: Benchmarking Local vs Cloud LLMs on a Real Coding Task

Last post we stood up Ollama on the RTX 5090, pulled a stack of models, and wired them into our...