💻 Agent mode just went local! Today, Mistral AI... released Devstral, an Apache-2.0, 24B-parameter model trained for tool calling in real-world software development environments It reached #1 on SWE-bench for open-source models, but more importantly in our real-world testing it has proven to be capable of navigating and autonomously editing codebases, while running entirely on a laptop To try it out, just add `ollama/devstral` in Continue. See below for a quickstart with ollama👇show more

it's open source time, with a real leap for... world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!show more

It's fast!! Ollama now supports AMD graphics cards! All... the features of Ollama can now be accelerated by AMD graphics cards in preview on Ollama for Linux and Windows. Try it 👇👇 *video is not edited.show more

i found a way to make UNCENSORED AI AGENT... on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have funshow more

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive... world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.show more

Qwen has just released a model on par with... GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details belowshow more

Open UI Local 1 Click Launcher Open UI from... wan deeee bee is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama Make sure to check out Matthew Berman's tutorial, and run it with 1 click.show more

Wow Mistral has released its new model tailor-made for... AI code assistants Codestral 25.01 (that's its name) is debuting at #1 on the LMsys copilot arena leaderboard 🔥 You can already use it for free in Continue (100% open-source) for VS Codeshow more

An 100% open-source rival to n8n just launched. Sim... is a drag-and-drop platform for building agentic workflows that runs entirely on your local machine. → Visual, Figma-like canvas interface → Works with any local LLM via Ollama → Native MCP support to connect 100+ toolsshow more

We just released a demo for our game, Cursemark.... It's an ARPG/Roguelike hybrid, with a lot of buildcraft and exploration in a dark fantasy world. Try it out and let us know what you thinkshow more

The leading model runnable on a single cloud H100... GPU now fits on a single home GPU! 🔥 We've optimized Gemma 3 27B with QAT so you can run our best-in-class open model on your desktop RTX 3090 or similar. See how easy it is to try via ollama! 👇show more

We just shipped Gemini 2.5 Pro as an available... model in Agent Mode. Try it out!show more

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

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

today, we're releasing an open version of Krea-1. FLUX... Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇show more

Today Meta released "Code Llama", a large language model... fine-tuned for coding tasks. It's publicly available and can be used for commercial use! It outperforms GPT 3.5 and you can even run it locally on your Macbook using Ollama.show more

Our models run real time on a laptop 5090... at 100+ FPS. We're so excited for people to start playing with it.show more

Right now, you may not have access to models... like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.show more

Just for fun, I tried training a 3D AI... model. Made one that can tell cubes from other objects. Trained it on my laptop CPU with only 100 samples in 7 seconds Next time I’ll try something more advanced. #b3d #blender3dshow more

India can’t be left behind in AI. कृत्रिम has... accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!show more

New Generation Model! 🚨 We're introducing the Mistral model... to our expanding lineup of generation models. Mistral brings efficient performance and strong language understanding capabilities to our platform. Initial testing shows promising results in code comprehension and generation tasks, making it a valuable addition to development workflows. While we continue to optimize its implementation, early benchmarks demonstrate consistent and reliable outputs across various programming tasks.show more