Can I run AI locally?(canirun.ai)

1375 points by ricardbejarano 7 months ago | 326 comments

CanIRun.ai is a web tool that estimates which AI models your machine can run locally, using browser APIs to detect hardware and grading each model's expected performance.

MicroLLM Lab – Try 7 tiny LLM's in the browser(stateofutopia.com)

271 points by logicallee 27 days ago | 99 comments

MicroLLM Lab is a browser-based tool for running, chatting with, and benchmarking small quantized language models locally via WebGPU with no server.

OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)(developers.openai.com)

312 points by tosh 2 months ago | 285 comments

GLM-5.2 – How to Run Locally(unsloth.ai)

559 points by TechTechTech 4 months ago | 266 comments

Unsloth documentation guide explaining how to run Z.ai's GLM-5.2 open model locally using Unsloth Dynamic quantized GGUFs.

Gemma3 – The current strongest model that fits on a single GPU(ollama.com)

212 points by brylie 1 year ago | 86 comments

Ternlight – 7 MB embedding model that runs in browser (WASM)(ternlight-demo.vercel.app)

304 points by soycaporal 3 months ago | 60 comments

Show HN: NSL – WSL for Linux(frostyard.github.io)

142 points by bketelsen 27 days ago | 86 comments

Project page for nsl, a tool that gives Linux hosts persistent distro environments via systemd-nspawn containers in a small VM, mimicking WSL.

Show HN: What if the speed of light was 5 km/h?(rivendell.dmitrybrant.com)

544 points by dmitrybrant 1 month ago | 236 comments

Interactive 3D browser simulation of a park where the speed of light is 5 km/h, showing length contraction, time dilation, Terrell rotation and Doppler effects.

Show HN: Linkpreview, see how your sites looks in social media and chat apps(linkpreview.xyz)

329 points by fayazara 2 years ago | 81 comments

LinkPreview is a web tool that shows how a URL's link preview will appear on social media and chat apps based on its meta tags.

Show HN: I built a web framework in C(github.com)

374 points by ashtonjamesd 1 year ago | 183 comments

GitHub repository for Lavandula, a fast, lightweight MIT-licensed web framework written in C for building web applications.

Quickemu: Quickly run optimised Windows, macOS and Linux virtual machines(github.com)

411 points by overbytecode 2 years ago | 128 comments

GitHub repository for Quickemu, a tool that quickly creates and runs optimised Windows, macOS and Linux desktop virtual machines using QEMU.

How fast is N tokens per second really?(mikeveerman.github.io)

459 points by hexagr 5 months ago | 94 comments

Interactive web tool that simulates LLM output streaming at selectable tokens-per-second rates for code, text, thinking, and agent modes.