Results for “apple”

Groupe KA — site du holding + KA ID (compte unique & SSO des 7 plateformes). Next.js 16, SQLite, Google & Apple login.

TypeScriptnextjstypescriptsqliteoauthssoapplegoogle

Internal cartography of local LLMs on Apple Silicon — registered, gated, negative-first. Public atlas at modelmap.io.

Pythoninterpretabilityllmapple-siliconmlxreproducibility

Agent personnel 100 % on-device — SwiftUI + Apple Foundation Models + EventKit + SwiftData. Aucune API, aucun serveur.

Swiftiosswiftswiftuifoundation-modelson-devicellmagentapple-intelligence

Forge — LLM training from scratch in pure C++20 + Metal on Apple Silicon.

C++llmtrainingcppmetalapple-silicon

Systematic discovery & rigorous validation of statistical anomalies in open HF market data (hfmarketdata.io) — pre-registered, artifact-null-driven, fully reproducible. Live atlas: www.anomaly-atlas.io

Pythonquant-researchmarket-microstructureanomaliesreproducibilityduckdbapple-silicon

Running LLMs larger than memory on a consumer Mac — falsification-driven research: margin-gated deferred refinement, out-of-core verification on Apple Silicon. TR-01 published.

Python

Stata-class statistics, GPU-accelerated by Apple Silicon. Native Swift — no Electron, no Python runtime, no compromises.

Swiftmacosswiftstatisticsgpu

The Instruments of LLM training — a native macOS cockpit for Forge. Train language models from scratch on Apple Silicon without a terminal.

Swiftmacosswiftaimlxtraining

Native macOS AI chat that runs LLMs 100% locally on Apple Silicon with MLX — no cloud, no API keys.

Swiftmacosswiftaimlxlocal-llm

Tendril — web ingestion platform (scrape/crawl/map/search) on macOS Apple Silicon: WebKit fidelity, authenticated pages, deterministic testable extraction. A self-hosted Firecrawl alternative.

JavaScriptweb-scrapingcrawlerwebkitmacostypescriptfirecrawlswiftfastify

spboucher.aimain

polyllmmain

phi-conseilmain

datacenterindexmain

sp-calendarmain

uqo-evalmain

vrai-prixmain

groupe-kamain

ka-statsmain

sorti-kamain

spinzamain

market-atlasmain

datacenterindexmain

internetpressuremain

satelliteindexmain

cancerindexmain

websensormain

rareindexmain

ai-atlasmain

countryatlasmain

llm-api-toolkits2a901f4Simon-Pierre Boucher2 days ago

llm-api-toolkitsc7d4113Simon-Pierre Boucher2 days ago

firc0001_uqo906fea1Simon-Pierre Boucher6 days ago

job-ka67cf3c22Simon-Pierre Boucher2 mo ago

fabri-ka59b1536Simon-Pierre Boucher2 mo ago

lou-kaafc49f6Simon-Pierre Boucher2 mo ago

spbgit2c84d42Simon-Pierre Boucher3 mo ago

spboucher.ai68a025cSimon-Pierre Boucher3 mo ago

…'identité centrale du groupe — un seul compte (courriel + mot de passe, Google, Apple, lien magique) et un partagé par toutes les plateformes via un SSO maison , avec carte de membre, passe Apple Wallet, favoris unifiés…

…maps the internal structure of pretrained open weight LLMs entirely on consumer Apple Silicon — and publishes the results as a reproducible, confidence labeled public atlas at modelmap.io . Every map is versioned, proven…

…rs ligne. Privé. Rien ne quitte ton iPhone. 5E5CE6) %20upload%C3%A9 0D96F6?logo=apple) Agent personnel local : chat, rappels, calendrier, notes, tâches et recherche sémantique — propulsé exclusivement par le modèle Apple…

🔥 Forge LLM training from scratch — pure C++20 + Metal on Apple Silicon No PyTorch. No MLX. No ML dependencies. Just C++, Metal kernels, and a JSON parser. 📄 Paper · 🔬 Research notes · 📐 Spec ✨ What this is A complet…

…tion Can an existing pretrained LLM whose memory requirements exceed a consumer Apple Silicon Mac be transformed post training into an execution representation whose instantaneous working set is dramatically smaller than…

Metrika Stata class statistics, GPU accelerated by Apple Silicon. Native Swift. No Electron. No Python runtime. No compromises. One session: a cluster robust factor variable regression, then a 10,000 replicate pairs boot…

…aining — a native macOS cockpit for Forge Train language models from scratch on Apple Silicon without ever opening a terminal. Pick a dataset, shape an architecture, hit Start — and watch the loss fall on a silky live da…

…ry native macOS AI chat client that runs large language models 100 % locally on Apple Silicon with MLX — no API keys, no cloud, no data ever leaving your machine. ⬇️ Download the latest DMG · Developer ID signed · Notari…

…Six native macOS applications for AI and local LLMs — Swift/SwiftUI, built for Apple Silicon. App Description Links ☁️ Zyquo Cloud Multi provider AI chat — Anthropic, OpenAI, and more in one unified interface Repo · Rel…

…54 (6 Mixed) · 0.032 · 11.1 % 2.1 s \ greedy decoding, 600 character paragraph, Apple GPU (MPS) on m4mm, measured 2026 11 10 (3 000 characters: Flan T5 ≈6 s, Qwen ≈8 s); live values at . Detector sensitivity (Pangram 4.1…

…lingual (English/French) research site documenting MacLustr, a personally owned Apple Silicon cluster. It is a technical showcase and research log, not a commercial service. Stack Next.js 16 (App Router, static generatio…

…t ⚡ 12 FSA fixed effects · Conley / cluster SE comparison 20 s ⚡ = under 5 s on Apple Silicon. Fully deterministic (seed 42). 🗃 Data Dataset Source Raw → Clean Key fields Airbnb listings Airbnb (scraped, early 2026) 5,0…

…a retrained neural model reproduces to within the five seed band. All runs used Apple Silicon (MPS) without mixed precision. Keywords · · · · · · JEL C45, C53, C58, G12, G17 📚 How to cite ℹ️ Below: documentation of the…

…d, peer reviewed version 1.1) — Asks which high frequency econometric workloads Apple's FP32 only GPUs can run while matching an FP64 reference, and when that is faster than a symmetric multicore CPU kernel: on one year…

…t yet submitted Journal — Code & data fully reproducible from + (≈ 10 min on an Apple silicon laptop) 🎯 What this paper does A listing card is a bundle of characteristics priced by its host. Following Rosen (1974) and L…

…s KL 1.98 🗂 Repository layout 🚀 Quick start About 25 minutes end to end on an Apple silicon laptop (the modern panel estimation dominates); the simulations take about one minute on 12 cores. 🗃 Data Source Release obta…

…Predictive Expert Orchestration for Distributed Mixture of Experts Inference on Apple Silicon UQO Working Paper No. 33 — A Measured Systems Study on a Heterogeneous Mac Cluster TL;DR An MLX native MoE inference runtime w…

….9.dev17 (CaDiCaL 1.9.5, Glucose 4.1), drat trim built from source, gcc O2, one Apple Silicon node (16 cores). 🗃 Data No external data set. Every graph P(n,5) is generated from the definition by (two independent constru…

…adapter. 3.0× vs 1.92× Measured decode latency of eight sparse edits at 103M on Apple Silicon against the analytic operation count; dense writes are only 18 % slower than sparse ones, so per action dispatch overhead eras…

…useful information at the lowest measured end to end cost? Real experiments on Apple Silicon (MLX) with Qwen2.5 3B / Llama 3.2 3B, genuine two node cache transfer over a 1 GbE LAN, repeated handoff chains with an evalua…