lossless

Tag

Cards List
#lossless

ZXC: Lossless compression built for ultra-fast decode

Lobsters Hottest ↗ · 2026-10-14 Cached

ZXC 0.15.0 正式发布,这是一款面向“一次压缩、多次解压”场景的无损压缩库 libzxc,采用 C 编写,解压速度可达每秒数 GB,其各级别的解码速度均为 LZ4 的 1.5–2.8 倍,且输出体积相等或更小。

0 favorites 0 likes
#lossless

balrogg: demonically compacting (up to 15%) lossless Vorbis/Opus recompressor

Lobsters Hottest ↗ · 2026-09-03 Cached

balrogg is a command-line tool that losslessly recompresses Ogg Vorbis and Opus files, reducing their size by up to 15% with size reductions of 8-12% for Vorbis and 3-8% for Opus.

0 favorites 0 likes
#lossless

png2jxl: Convert PNG to lossless JPEG XL with byte-for-byte reconstruction of the original PNG

Lobsters Hottest ↗ · 2026-08-27 Cached

png2jxl is a Python tool that converts PNG images to JPEG XL format losslessly, allowing perfect reconstruction of the original PNG files.

0 favorites 0 likes
#lossless

@shaneparrish: https://x.com/shaneparrish/status/2075226155548807210

X AI KOLs Following ↗ · 2026-07-09 Cached

Demonstrates running two 80B Qwen models simultaneously on a MacBook Pro using BBQ-FP4 quantization, claiming functionally lossless performance and speed.

0 favorites 0 likes
#lossless

GetCompress

Product Hunt ↗ · 2026-06-24

GetCompress is a tool for lossless media compression without context switching.

0 favorites 0 likes
#lossless

Lossless GIF recompression via exhaustive search

Hacker News Top ↗ · 2026-06-23 Cached

Blog post exploring lossless recompression of GIF images using exhaustive search over LZW encoding, similar to Zopfli for PNG, to achieve smaller file sizes.

0 favorites 0 likes
#lossless

@Voxyz_ai: https://x.com/Voxyz_ai/status/2056043700757705122

X AI KOLs Following ↗ · 2026-05-17 Cached

Explains two memory patterns for AI agents: GBrain (queryable company wiki) and Lossless (full conversation recording), helping agents retain and retrieve facts across and within conversations.

0 favorites 0 likes
#lossless

Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution

Hacker News Top ↗ · 2026-05-15 Cached

Orthrus is a dual-architecture framework that combines autoregressive LLM fidelity with diffusion model speed, delivering up to 7.8x speedup on Qwen3 models while guaranteeing identical output distribution.

0 favorites 0 likes
← Back to home

Submit Feedback