RayCodes_HyMT2
Destroys Google Translate? Tencent’s New 440MB AI Runs 100% Offline (Hy-MT2 Review) - Offline SRT video subtitle translator powered by Tencent Hy-MT2 1.8B GGUF.
- 20
- Python
- 2 mo ago
47thtechcorner
Built from 47thtechcorner's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
Destroys Google Translate? Tencent’s New 440MB AI Runs 100% Offline (Hy-MT2 Review) - Offline SRT video subtitle translator powered by Tencent Hy-MT2 1.8B GGUF.
Parakeet Redux: Nvidia's 178MB AI Beats Whisper Running 113× Faster on CPU! - Lightweight, private CPU speech-to-text app powered by Moondream Parakeet Redux.
I Ran Qwen 3.8 27B on Just 4GB VRAM! (FreeToken Tutorial) - Edge-native MoE serving engine for local LLMs on low VRAM GPUs
Gemma 4 Just Got a 30ms Decision Brain! (Jeff Engine Setup) - A lightning fast 30ms decision agent using Jeff-Gemma4-E2B.
Google TimesFM 3.0: This Tiny 330M AI Can Predicts Stocks Locally! (CPU Setup) - Predict stock market prices and market trends using Google's TimesFM 3.0 foundation model locally on CPU.
KittenTTS 2: Clone Any Voice Locally In Just 2GB Size! - Zero-shot multilingual voice cloning pipeline running offline.
Clone ANY Website UI in Seconds! (REA AI Agent Setup) - Passive browser inspection and UI reconstruction of ultra-clean SaaS pricing layouts using REA & CDP.
Qwen 3.8 Memory Hack: This 0.8B AI Steals a 51B Brain Locally! (Qwengram Setup) - Local Python engine and Ollama setup for Qwengram-0.8B with transferred N-gram memory.
Humanizer Skill 3.0: Make AI Writing Sound 100% Human Locally! - Local AI prose humanizer skill for Ollama, Claude Code, and Skills CLI
This 5MB TTS Runs on CPU in 50ms! (sanoTTS Local Setup) - Efficient local text-to-speech voiceover pipeline
Indra OCR: Replace Google Tesseract & PaddleOCR on CPU - 1.25M vision AI model running 49 p/s on CPU with 0MB VRAM
Ternary Bonsai 2: New 0.4GB Vision AI With 310 Tokens/Sec Speed! - 100% private visual document scanner and PII redactor running locally.
Anatomy Skill 1.1 Just Got Better: Turns Agents Into 3D AI Illustrator! Turn code and technical concepts into interactive 3D and isometric mechanical machines in standalone HTML.
Run Qwen 3.8 27B on a 6GB GPU! (Ternary Bonsai 2 Setup) - Lightweight 1.76-bit ternary quantization implementation and local workflow
HyperFrames: New 100% Open-Source AI Video Engine for Local Agents! Write HTML, render 4K video with AI agents.
NaviDC-OCR: This Tiny 1.2B Model Beats Paid OCR APIs (100% Local) - Lightweight 1.2B open-source vision parser for local document & whiteboard OCR.
New #1 Agent Memory Beats GPT-4o With Cost! (Hindsight Setup) - AI stress-testing tool
Needle 3: This AI Is Only 29MB — Yet It Can Control Your Devices Offline!
YuE2-3B Destroys Suno: Full Music Generation on 4GB GPU! Autonomous AI songwriter that transforms social tweets into radio music.
Xiaomi MiMo V2.6: Qwen 9B Updated Coding Agent on 3GB VRAM! - Distilled 9B model for fast offline automation
This 4B Local AI Scores 96.9% on Coding! (NeoHorse Agent Setup) - Complete setup guide and python implementation for running NeoHorse 1-4B local autonomous agent with Ollama.
NVIDIA Parakeet 0.6B Upgrade: Run Orukeet AI on 2GB GPU! Offline Video Localizer & Auto-Subtitle Sync Generator.
ADHD Skill GitHub: This 10KB AI Tool Slashes Claude Code Costs by 89%! - Open-source prompt skill & agent harness plugin to slash AI token costs.
Craft Anything GitHub: Clone ANY App UI in Seconds Without Code! Clean-room reverse engineering & reconstruction engine with 320 compiled inspection probes for local coding agents.