LATEST FEEDS

llm

Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

ByteShape's full ShapeLearn release of Qwen 3.8 27B: five GGUF models on the measured quality-speed frontier across RTX 3090, 4080, 4090, 5060 Ti, 5090 and RTX Pro 6000. GPU-5 is the default wherever it fits, at 99.63% of BF16. GPU-4 stays very competitive at 98.72% in a much smaller file. Plus why ShapeLearn-Lite beat its KLD ranking, and MTP versus DFlash2 speculative decoding.

RECENT ARTICLES

More Programming Articles
01

PageSaver vs GoFullPage: Which Fits Your Screenshot and PDF Workflow?

GoFullPage makes it easy to capture an entire webpage. PageSaver is an alternative worth considering when you also want clean reading copies, Markdown exports, Firefox support, or tools for working with the PDF after you save it.We build PageSaver, PixelPDF, and PageSaver PDF for…

04

Meta Quest 4 Five Less Obvious Capabilities Graded by Evidence

Ask what Meta Quest 4 will do and most answers reach for pixel counts and a launch window. Both are guesses. For people who write software rather than read spec sheets, a better question is narrower: which capabilities have real technical evidence behind them, and how strong is i…

06

Why You Can't Test a Chrome Extension the Normal Way

I've been building browser extensions for a few years now: PageSaver, which turns a web page into a PDF or an image, and a handful of others. Every one of them shipped without a single automated test. Not because I didn't want tests, but because the tools I already knew couldn't …

Explore