MoE Models

MoE Models SpikingBrain: 100x Faster LLM Inference via Spike Sparsity

SpikingBrain leverages brain-inspired spike sparsity and Mixture of Experts (MoE) to drastically reduce LLM latency. It achieves a 100x TTFT speedup on 4M token sequences and supports MetaX or NVIDIA GPUs.

MoE Models Dots.LLM1: 142B MoE Model Trained on 11.2T Real-World Tokens

Dots.LLM1 is a 142B total parameter MoE model with 14B activated. Trained on 11.2T tokens of real text, it rivals Qwen2.5-72B in performance at a lower computational cost.

System Utilities Checkmate: Open-Source Server Monitoring with Uptime Alerts

Checkmate is a self-hosted monitoring tool for servers, websites, and Docker containers. Track uptime, CPU usage, memory, and page speed with alerts sent via Slack, Telegram, and email.

System Utilities Windows-Use: Enabling LLMs to Control the Windows GUI Without Vision Models

Windows-Use connects large language models directly to the Windows GUI. It enables AI agents to open apps, click, type, and capture UI states without relying on computer vision.

LLM Tooling LLM Bridge: A Unified API Schema for OpenAI, Claude, and Gemini

LLM Bridge streamlines communication between OpenAI, Anthropic, and Google Gemini APIs with zero data loss. Utilize a single, type-safe universal format that fully supports tool calls and multimodal content.

System Utilities mRemoteNG Setup: Manage RDP, SSH, and VNC in One Tabbed Console

A step-by-step mRemoteNG setup guide for Windows 11 and Server. Learn how to perform silent MSI installs, organize connection panels, and launch external applications like FileZilla using variables.

System Utilities Flameshot CLI Guide: Capture, Edit, and Upload Screenshots Rapidly

A comprehensive Flameshot command-line reference featuring GUI, full-screen, and delayed capture examples. Includes configuration tips, keyboard shortcuts, and installation guides for Linux, macOS, and Windows.