Sign in

Repository Index

142,187 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

361–384 of 427 · Most stars

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

Desbordante is a high-performance data profiler that is capable of discovering many different patterns in data using various algorithms. It also allows to run data cleaning scenarios using these algorithms. Desbordante has a console version and an easy-to-use web application.

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.

Open-source parametric 3D CAD for makers — constraint sketches, solid modeling, threads, SVG & text engraving, STL/STEP export. Android, iPad, Linux, Mac, Windows. Vibe coded.

Unofficial native Android port of Need for Speed: Most Wanted (Xbox Black Edition). The x86 code is statically recompiled to C++ with XboxXBE-Recomp and built for arm64, with a Vulkan renderer, SDL3, touch/controller/keyboard input, and extended graphics options. No emulator, no game assets included.

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.

  • ampere
  • consumer-gpu
  • cuda
  • ggml

An unofficial native Android port of the original Xbox version of Black, with touch controls, gyroscope aiming, controller support and extended graphics options.

SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.

  • ascend
  • audio
  • audio-generation
  • diffusers

C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer

Leonardo AI 2026 desktop setup with text-to-image generation using fine-tuned models, canvas editor with inpainting and outpainting, plus real-time generation and image-to-motion for Windows 11

  • ai-art-platform
  • ai-creative-suite
  • ai-generation-tools
  • ai-image-generator

Adobe Acrobat PDF 2026 desktop setup with text and image editing directly inside any PDF, conversion to and from Word, Excel and images, plus fill, sign and merge documents with an AI assistant for Windows 11

  • acrobat-dc-pro
  • acrobat-for-free-2026
  • acrobat-no-limits
  • acrobat-pdf