AILLM
13 min read
TurboQuant + MTP: Get 40.6 tok/s Out of Qwen3.6
How to build llama.cpp w/ TurboQuant and MTP and use it on consumer HW - 32GB RAM + 8GB VRAM GPU.
Automation & Tools
A technical journey through Playwright snippets, AI-driven testing, and the automation playbooks of everyday QA engineering.
Latest Insights
Showing 4 Total Articles
PlaywrightHAR
10 min read
Playwright v1.60’s HAR Recording: The Debugging Superpower You Didn’t Know You Needed
Playwright v1.60 introduces scoped HAR recording that captures every network request and response during a failing test, turning failures into consumable evidence for humans and AI. This guide dives deep into the new `tracing.startHar()` API, shows real-world patterns, and reveals gotchas you'll encounter in CI.
AILLM
15 min read
Taming a 26B MoE Model on 8GB VRAM with TurboQuant
Forget Docker images and pre-built binaries. Here's how I compiled a custom llama.cpp fork with TurboQuant, ran a 26B Gemma 4 MoE model on a consumer RTX 3070, and squeezed 262K context into less than 4GB of VRAM.
AIOpenCode
6 min read
Deploying Qwen3-Coder-30B-A3B on 8GB GPU with Docker
A 30B model on an 8GB GPU sounds impossible, but quantization and llama.cpp make it work. This guide shows how to run it with Docker and use it in OpenCode.