News

May 29, 2026
NuExtract3 Turns Sensitive Docs Into Markdown Without The Cloud

NuExtract3 is a new 4-billion-parameter vision-language model that extracts structured data from documents and converts them into Markdown. It handles text, images, or both at once, making it suitable for […]

Read More
May 29, 2026
MiniCPM5-1B: One Model, Dual Modes for Fast Chat or Deep Thought

MiniCPM5-1B is a small 1-billion-parameter language model designed to run locally on personal devices and in low-resource settings. The same checkpoint can work as a fast everyday assistant or a […]

Read More
May 29, 2026
LongCat-Video-Avatar-1.5 Materializes Studio-Quality Talking Heads Locally

LongCat-Video-Avatar-1.5 is a new open-source model for generating talking avatar videos from audio paired with text or image references. It produces realistic human characters, stylized animations, and coordinated multi-person conversations […]

Read More
May 29, 2026
BigStationW Delivers ComfyUi-Untwisting-RoPE For Style Without Copying

BigStationW has released ComfyUi-Untwisting-RoPE, a custom node for ComfyUI that brings training-free style transfer to diffusion transformer (DiT) models. The tool tackles a common problem where shared attention mechanisms accidentally […]

Read More
May 29, 2026
OpenReader Preloads Audio, Makes Every Document a Private Audiobook

OpenReader v3.0.0 is a self-hosted web application that reads EPUB, PDF, TXT, Markdown, and DOCX files aloud while highlighting each word in sync. It functions as a private document reader […]

Read More
May 28, 2026
New Gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic

The Gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic is a fine-tuned version of Google’s Gemma 4 31B instruct model that cuts content refusals dramatically while sharpening its writing style. It starts from an already decensored base, […]

Read More
May 28, 2026
G4-MeroMero-31B-uncensored-heretic Slashes 85% Refusals For Creators

G4-MeroMero-31B-uncensored-heretic is a newly released language model that strips away almost all refusal behaviors. It builds on a fine-tuned version of Google’s Gemma 4 31B designed for storytelling and roleplay. […]

Read More
May 28, 2026
Gemma-4-Gembrain-31B-It-Uncensored-Heretic Slashes AI Refusals By 87%

Gemma-4-Gembrain-31B-it-uncensored-heretic is a stripped-down version of Google’s Gemma 4 31B instruct model that says “no” far less often. It was built with the Abliteration technique to remove most safety refusals […]

Read More
May 28, 2026
SmallCode Debuts: Local Coding Agent Squeezes Power From Small LLMs

SmallCode is a terminal-based coding agent for local language models between 8B and 35B parameters. It operates fully on your own hardware, keeping code private and avoiding cloud costs. Its […]

Read More
1 3 4 5 6 7 59