08:51 Tutorials1 week ago OpenJarvis + Ollama: Local AI Agent That Tracks Every Watt Fahd Mirza walks through the installation and hands-on testing of Open Jarvis, a newly released local-first personal AI framework dev... 0 comments 2.1K views
10:04 Research & Benchmarks1 week ago Mistral OCR 4 Is Built Different – 170 Languages, and Does It Beats Them All? Fahd Mirza, a Mistral AI ambassador, delivers a no-hype hands-on review of Mistral OCR 4, the company's new document extraction model... 0 comments 1.5K views
10:25 Coding & Dev Tools2 weeks ago PixelRAG Locally: RAG That Reads Screenshots Instead of Text Standard RAG pipelines fail silently on documents with complex layouts: when HTML-to-text parsers mangle tables and charts, the retri... 0 comments 1.2K views
21:01 Research & Benchmarks2 weeks ago GLM-5.2 vs MiniMax-M3 vs Qwen3.7-Max — 3 Coding Tests, One Winner Fahd Mirza runs a hands-on three-way coding showdown between GLM-5.2, MiniMax M3, and Qwen 3.7 Max using the Hermes agent framework.... 0 comments 2.2K views
09:36 Benchmarks2 weeks ago Qwen3.6 (REAP 90pct GGUF): The Brain-Damaged Model Fahd Mirza takes a deep look at an aggressively pruned variant of Qwen 3.6 — a 35-billion-parameter mixture-of-experts model — compre... 0 comments 2.8K views
14:42 Tutorials2 weeks ago Qwen3.6 27B (Pi-Reasoning GGUF) – Fine-Tuned for Local Heavy AI Agent Fahd Mirza tests Pi-Reasoning, a community fine-tune of Qwen 3.6 27B built specifically for agentic coding — tasks like reading files... 0 comments 3.8K views
08:05 Tutorials2 weeks ago Dots.TTS SOAR – State of the Art Speaker Similarity, Runs Fully Local Fahd Mirza walks through the installation and hands-on testing of Dots.TTS SOAR, a fully open-source zero-shot voice cloning model th... 0 comments 1.8K views
09:07 Coding & Dev Tools2 weeks ago Luce KVFlash: Finding a Needle in 256K Tokens with Low VRAM Fahd Mirza runs a controlled needle-in-a-haystack experiment to test whether Luce KVFlash can reliably retrieve a specific fact from... 0 comments 1.6K views
12:46 Coding & Dev Tools3 weeks ago VibeThinker-3B: 3B Model That Challenges Claude Opus? Test Locally Fahd Mirza installs and tests VibeThinker-3B — a reasoning model released by Weibo, the Chinese social media giant — directly on an N... 0 comments 2.7K views
10:03 Coding & Dev Tools3 weeks ago GLM-5.2: Anthropic Got Banned. China Shipped Same Night: Hands-on Testing Fahd Mirza delivers a hands-on test of GLM 5.2, the latest model from Chinese lab ZAI (Zhipu AI), released the same evening Anthropic... 0 comments 2.8K views