raphlinus/nibnib

Consistently faster and smaller compressed bitmaps with Roaring | Daniel Lemire, Computer Science Professor

Computer Science Professor

PrismML — Introducing Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

Ternary Bonsai 2 27B retains 98.2% of Qwen3.8 27B benchmark performance in a 5.9GB footprint, with multimodal and agentic capabilities.

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.

Vanilagy/turbores

An extremely fast WASM Apple ProRes video decoder

Better bitmap performance with Roaring bitmaps

Bitmap indexes are commonly used in databases and search engines. By exploiting bit-level parallelism, they can significantly accelerate queries. However, they can use much memory, and thus we might prefer compressed bitmap indexes. Following Oracle's lead, bitmaps are often compressed using run-length encoding (RLE). Building on prior work, we introduce the Roaring compressed bitmap format: it uses packed arrays for compression instead of RLE. We compare it to two high-performance RLE-based bitmap encoding techniques: WAH (Word Aligned Hybrid compression scheme) and Concise (Compressed `n' Composable Integer Set). On synthetic and real data, we find that Roaring bitmaps (1) often compress significantly better (e.g., 2 times) and (2) are faster than the compressed alternatives (up to 900 times faster for intersections). Our results challenge the view that RLE-based bitmap compression is best.

TinyPNG – Compress AVIF, WebP, PNG and JPEG images

Free online image optimizer for faster websites! Reduce the file size of your AVIF, WEBP, JPEG and PNG images while preserving the image quality.

b-nnett/grok-bot-0.18-reconstructed

Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS

Perceptual coding

Perceptual coding is a method of lossy data compression that exploits the limitations of human sensory system in order to reduce data size. It is widely applied in audio, image and video compression standards, where certain details are removed or simplified because they are unlikely to be noticed under regular listening or viewing conditions.

Z-Image - Efficient Image Generation with Single-Stream Diffusion

Z-Image: A powerful and efficient 6B-parameter image generation model with support for bilingual instructions and fast inference.

A 16× Smaller Index for EmbeddingGemma 2

EmbeddingGemma 2’s one advertised way to shrink its vectors, keeping 128 of 768 dimensions, loses about 0.06 nDCG@10. Storing all 768 at 2 bits each is 16× smaller with no measurable loss on SciFact or NFCorpus.

AOMediaCodec/libavif

libavif - Library for encoding and decoding .avif files

DISPLAY PREP DEMO

This demo was designed to be viewed in full raster with visually lossless image files, but is presented here in compromised format to make possible wider distribution.

Dynamic 1-bit DeepSeek-R1-0528 GGUFs out now!

118 votes, 16 comments. Hey guys sorry for the wait, but now you can now run DeepSeek-R1-0528 with our Dynamic 1-bit GGUFs!…