RigSpark: know which AI will run on your own computer
RigSpark reads a machine's memory, GPU and disk and shows which open models and sizes will actually run on it, which will be slow, and which will not run, then runs chat, images, video and voice locally with no account, cloud or metering.
Why it matters
The first step of local AI is a guessing game that wastes 30-40GB downloads: RigSpark answers 'will it run on my machine' before the download starts, then becomes the runner itself.
What you could build with it
A hobbyist with a mid-range GPU could run RigSpark first to learn which open models actually fit their machine, then download only the ones that will run instead of wasting hours on a 40GB file their hardware cannot load.
Does it hold up?
Usable today for its core job: free, open-source, reads local hardware and lists what fits before a big download; 38 releases since August show active maintenance, though only 22 GitHub stars so far.
Built with RigSpark
- How to Use RigSpark AI for Beginners (Free Local AI Guide)aitoolsteps · Hands-on beginner guide: hardware scan, yes/slow/no verdicts per model, and running chat, images, video and voice offline.
- RigSpark: Know which AI to run on your own computerproducthunt · Product Hunt launch page: reads memory, GPU and disk, shows what fits before a 30–40 GB download, then runs models locally with no account or cloud.
- rigspark-cli 3.1.3 — Docs.rsdocs.rs · CLI crate docs: fit checks, Hugging Face models, offline chat, and rigspark connect to point coding agents at a local model.
Learn more
First spotted on github: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.