local.ai

Local AI Management, Verification, & Inferencing.Experiment with AI offline, in private. No GPU required! - A native app made to simplify the whole process.Free and open-source.Your browser does not support the video tag.Starting an inference session with the WizardLM 7B model in 2 clicks..MSI.EXEM1/M2IntelAppImage.debYour browser does not support the video tag.Power any AI app, offline or online. Here in tandem with window.ai.Powerful Native AppWith a Rust backend, local.ai is memory efficient and compact. (<10MB on Mac M2, Windows, and Linux .deb)Available features:CPU InferencingAdapts to available threadsGGML quantization q4, 5.1, 8, f16Upcoming features:GPU InferencingParallel sessionModel ManagementKeep track of your AI models in one centralized location. Pick any directory!Available features:Resumable, concurrent downloaderUsage-based sortingDirectory agnosticUpcoming features:Nested directoryCustom Sorting and SearchingDigest VerificationEnsure the integrity of downloaded models with a robust BLAKE3 and SHA256 digest compute feature.Available features:Digest computeKnown-good model APILicense and Usage chipsBLAKE3 quick checkModel info cardUpcoming features:Model ExplorerModel SearchModel RecommendationInferencing ServerStart a local streaming server for AI inferencing in 2 clicks: Load model, then start server.Available features:Streaming serverQuick inference UIWrites to .mdxInference paramsRemote vocabularyUpcoming features:Server Managet/audio/image.MSI.EXEM1/M2IntelAppImage.deb