A peanut-sized Chinese model just dethroned Gemini at reading... documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.show more

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR... is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!show more

Unlimited-OCR is a 3B parameter model that parses entire... 100-page PDFs in one shot — no page chunking, no lost context. +⁠32K context window, reads the whole document in a single pass +⁠93% on standard parsing benchmarks, +6 over baseline +⁠Under 0.11 error rate past page 40 — where every other OCR tool falls apart ⁠+Multilingual out of the box, runs locally via Transformers, Ollama, llama.cpp, Docker +⁠Textract, Google Vision, and Azure Doc Intelligence charge $1.50–$15 per 1,000 pages 1.9M downloads on HuggingFace and most people have never heard of it. This runs on your machine. For free. Forever. Model link:show more

China open-sourced a peanut-sized OCR that parses entire 100-page... PDFs in one shot.. It's called Unlimited-OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass. → One-shot "long-horizon" parsing (32K context window) → Multilingual, out of the box → 93% on the standard parsing benchmark (+6 over baseline) → <0.11 error rate past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50–$15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it explicitly to push DeepSeek-OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet. 100% open source.show more

Baidu just open-sourced an OCR model that reads entire... 40-page documents in one shot. It's called Unlimited-OCR. 3 billion parameters but only 500 million active during inference. Runs 100% locally on your machine. Why this matters: traditional OCR tools chop documents page by page. Tables that span two pages break. Reading order gets lost. Cross-page context disappears. Unlimited-OCR processes the whole document at once. 32K context window. Text, formulas, tables, reading order all preserved across pages. Output comes out as clean structured Markdown. → 93% accuracy on the standard benchmark. +6 points over the baseline. → Error rate stays below 0.11 even past 40 pages. → Multilingual out of the box. → 2.12 million downloads on Hugging Face last month. 14,600 GitHub stars. For context: Amazon Textract, Google Cloud Vision, and Azure Document Intelligence all charge per page. This runs locally for free.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

NVIDIA just made AI detect objects 10x faster by... deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.show more

You can now use GPT 5.5, Gemini 3.7 Flash,... Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.show more

Claude cannot watch a YouTube video, Instagram reel, Tiktok,... or local file video. Same problem is with ChatGPT and Gemini. It reads the transcript and pretends it did. This FREE AI TOOL fixes this issue It extracts only the important frames, transcribes the audio, and hands Claude a clean folder it can genuinely read and understand. No uploading to a server. Runs entirely on your machine. Here is what makes it smarter than everything else doing this: → Detects scene changes instead of grabbing one frame per second like every other tool → Removes near-duplicate frames so Claude is not reading the same shot 40 times → Handles A-B-A cuts, if a shot already appeared, it does not send it again → A 10-minute static screencast collapses to 1 frame instead of 600 → A fast-cut reel catches every visual change instead of missing frames between samples → Transcribes audio with Whisper and auto-detects the language → Saves the full soundtrack so audio models can actually hear it too → Works with Claude, ChatGPT, and Gemini The result: fewer frames, cheaper context, better understanding. Claude actually sees the video instead of guessing from a transcript.show more

1 mini PC that fits in a palm, with... no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.show more

Building RAG is easy. Parsing real, unstructured data is... the hard part. Most tools fail when documents get complicated. RAGFlow by InfiniFlow makes the entire process visual and flawless 🔥 It is an (open-source!) engine built specifically to find the exact needle in a data haystack, even across literally unlimited tokens. The platform comes packed with: → "Quality in, quality out" parsing for highly complex formats → Multiple recall paired with fused re-ranking → A built-in Python and JavaScript code executor for agents → An orchestrable ingestion pipeline Here's why it stands out: 1️⃣ Structural Understanding Instead of just scraping text, it handles tables across pages, scanned copies, slides, and Excel sheets natively using deep document understanding. 2️⃣ Grounded Citations Every answer is verifiable. The UI highlights the exact chunks used, allowing you to trace any response directly back to the source material. 3️⃣ Enterprise Synchronization Keep your context constantly updated with native data sync from Google Drive, Notion, Discord, and Confluence. Stop letting bad document parsing ruin your RAG systems. Best part? It's 100% Free and open-source. Link to the repo in 🧵↓show more

THIS GUY IS BUILDING INSANE CUSTOM SITES FOR $0.23... IN API COSTS WITH THE NEW KIMI K3 currently #1 on the coding arena. the video attached shows a complex, highly detailed website. it was coded entirely by a new model called Kimi K3. early testers are calling it scarily good because it quietly removes the need for complex agent swarms. here is the instant breakdown of what makes it terrifying. 1. native vision in the loop it iterates code while analyzing live screenshots of its own output. it literally looks at the site it builds and corrects the styling autonomously. 2. massive sparse architecture it has 2.8 trillion parameters but only activates 50b per token. this makes it insanely fast and allows for a native 1,000,000 token context window. 3. recursive self-improvement it spends a massive amount of compute on self-verification. it runs unit tests and simulates environments before giving you the final frontend code. 4. brutal economics it costs exactly $3 per million input tokens. the entire custom site in the video cost around $0.23 to generate. the era of orchestrating 12 dumb agents to build a simple web app is over. one smart instance is all you need.show more

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T... RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.show more

🚨 Alibaba just open sourced a GUI agent that... lives inside your webpage and controls it with natural language. It's called Page Agent and it's not a browser extension. It's pure JavaScript no Python, no Puppeteer, no headless browser, no screenshots. Just one script tag and your web app understands natural language. Here's what it actually does: → Embed it with a single tag or npm install → Control any web interface with plain English commands → Text-based DOM manipulation no OCR, no vision models needed → Bring your own LLM (GPT, Claude, Qwen, anything) → Ships a built-in UI with human-in-the-loop support → Turn 20-click ERP/CRM workflows into one sentence → Optional Chrome extension for multi-tab agent tasks → Works on any web app SaaS, admin panels, internal tools Companies are charging $30/month for AI copilots built on this exact idea. This is 3 lines of code. Your users. Your interface. The AI copilot layer for every web app just got open sourced. 1.6K stars. 100% Open Source. (Link in the comments)show more

GLM 5.2 INPUT FELL FROM $1.40 TO SEVEN CENTS... PER MILLION IN NINETY DAYS • what it costs now > $0.07 per million input at the cheapest of 20 providers, a 95% drop in three months. > direct still lists $1.40 in and $4.40 out, with cached input at $0.26. > Same model, same weights, twenty-fold spread depending on the door you walk through. • the free way in > New accounts on get 20M tokens: > 744B MoE, 1M context, MIT weights you can also just download and self-host. Nobody announced this. It happened one provider at a time -> and the model itself never changed. Check which provider you are actually routed through before you top up anywhere ↓show more

Gemini Omni is changing video creation and most people... still don't know what it can actually do. Here are 7 things you can do with it right now: 1. Image to Video in multiple styles: Upload a photo. describe the style. Gemini Omni turns it into a video. cinematic, anime, realistic. 2. Reimagine camera angles: Take any image and visualize it from a completely different angle. no reshooting. just describe it. 3. Change backgrounds: Swap the background of any video through plain conversation. no green screen. no editing software. 4. Change hairstyle: Describe a new hairstyle. Gemini Omni applies it. characters stay consistent across every frame. 5. visualize with moodboards: feed it a moodboard, audio, and a brief. it builds the video around the full creative reference — not just a text prompt. 6. swap characters and objects mid-scene: replace people, props, and objects in an existing video. the scene stays consistent. the physics hold up. 7. edit physics: describe how you want things to move. Gemini Omni adjusts the physics of the scene through conversation.show more

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech... model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.show more

Holy shit... Microsoft open sourced an inference framework that... runs a 100B parameter LLM on a single CPU. It's called BitNet. And it does what was supposed to be impossible. No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed. Here's how it works: Every other LLM stores weights in 32-bit or 16-bit floats. BitNet uses 1.58 bits. Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for. The result: - 100B model runs on a single CPU at 5-7 tokens/second - 2.37x to 6.17x faster than llama.cpp on x86 - 82% lower energy consumption on x86 CPUs - 1.37x to 5.07x speedup on ARM (your MacBook) - Memory drops by 16-32x vs full-precision models The wildest part: Accuracy barely moves. BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat. What this actually means: - Run AI completely offline. Your data never leaves your machine - Deploy LLMs on phones, IoT devices, edge hardware - No more cloud API bills for inference - AI in regions with no reliable internet The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine. 27.4K GitHub stars. 2.2K forks. Built by Microsoft Research. 100% Open Source. MIT License.show more

We removed 93.25% of the connections in our Un-0... image model, fully expecting to pay for it in quality. But it got better. FID 7.15 on ImageNet 64x64, roughly 1.9 ahead of the dense baseline at matched size. Same family of model, a fraction of the couplings, a better score. Here is why that is not as strange as it sounds. Un-0 is a coupled oscillator model, and in the dense version every oscillator talks to every other one. That sounds like a strength, but it means the whole system can fall into catastrophic synchronization: everything locks into step, gradients go flat, and learning stalls. Sparser connectivity leaves room for coherent and incoherent activity to coexist. The dynamics stay alive, and the model keeps learning. Connectivity turns out to be a control knob, not a dial you turn up until it stops. Learn more here:show more

MiniMax M3 just dropped — their first natively multimodal... model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.show more