Mediabunny v1.52.0 adds quantizer-based video encoding for AVC, HEVC, VP9, and AV1, enabling constant-quality video encoding.
A 4-Bit Model and a 1-Bit Index
Running NVFP4 Nemotron on a CPU, then mapping every embedding-compression method at matched byte budgets. The two quantizations compose.
Mediabunny — A complete JavaScript media toolkit for the browser | Mediabunny
A JavaScript library for reading, writing, and converting media files. Directly in the browser, and faster than anybunny else.
Reverse-engineering GGUF | Post-Training Quantization
Benjamin Marie on Twitter / X
Quantization and Qwen3-VL✔️ AutoRound W4A16 (INT4)✔️ AutoRound NVFP4 (llm compressor format)❌ support by vLLM (tried stable and dev releases)VLMs are now very easy to quantize. And then we can’t use the models with fast inference frameworks like vLLM and SGLang.It…— Benjamin Marie (@bnjmn_marie) November 5, 2025
Thireus/GGUF-Tool-Suite
Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain will create a GGUF recipe tuned to your hardware within seconds — flexible model sizing and lowest achievable perplexity/kld for GGUF enthusiasts seeking precise and automated dynamic quant production.
A 0-click exploit chain for the Pixel 9 Part 1: Decoding Dolby
Over the past few years, several AI-powered features have been added to mobile phones that allow ...
AI-Efficiency/Awesome-Model-Quantization
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.
Create and load standalone quantized UQFF models · Issue #947 · EricLBuehler/mistral.rs
I've been considering using mistral.rs for vision models as it's the only choice other than llama.cpp that support partial offloading; however, a few things I quickly noticed was that UQFF ...
Big Buck Bunny
Big Buck Bunny is now even more a world standard for video standards. Check this release: http://bbb3d.renderfarming.net/download.html
Unorthodocs: Abandon your DVCS and Return to Sanity - bitquabit
I’ve pretty much always been a DVCS apologist. I know quite a few people who’ve been using DVCSes since Mercurial and Git, and a few who go back to BitKeeper, but I can totally out-hipster you. I was there for Monotone. I actually remember struggling to grok tla, and being happy that someone took the time to write baz. I remember the promise and the failure that was Darcs. I remember thinking that even Darcs was comically primitive, because it was nothing but a poor imitation of Smalltalk DVCSes like Monticello, themselves mere iterative improvements on classic Smalltalk changesets.[1]
mikegee on Twitter / X
Controlling Figma with voice using Jev from @typesafeaiTotal cost from first line of code to recording this video: $0.01🤯 pic.twitter.com/HTGcrBYpTb— mikegee (@mikegee) September 18, 2026
A plugin that lets Claude Code watch videos; image + audio
177 votes, 67 comments. Claude doesn't natively accept video or audio input, so every time I wanted it to "look at a video" I'd have to screenshot…