Results for “llm”

The discriminative, contamination-resistant, fully transparent LLM ranking — updated live.

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

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

One local endpoint, every AI provider — a private OpenAI-compatible LLM gateway for your Mac (170 models, 12 providers).

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

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

Private universal chat interface over the OpenRouter ecosystem — 400+ models, branching, streaming, usage tracking. Next.js 16 + SQLite, PWA, deployed on m4m64a at chat.spboucher.ai

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.

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

company-atlas · main

wp45_uqo · main

qc26 · main

wp25_uqo · main

doc-api · main

wp25_uqo · main

ka6 · main

ka2 · main

ka4 · main

trawls · main

doc-api · main

doc-api · main

wp25_uqo · main

spboucher.ai · main

social-runtime-crawler · main

doc-api · main

wp37_uqo · main

wp25_uqo · main

firc0001_uqo · main

uqo-research-db · main

firc0001_uqo · 0ceee29 · Simon-Pierre Boucher · 3 days ago

firc0001_uqo · b7e79df · Simon-Pierre Boucher · 3 days ago

firc0001_uqo · 7680606 · Simon-Pierre Boucher · 3 days ago

wp37_uqo · a1cc09c · Simon-Pierre Boucher · 8 days ago

wp37_uqo · b5f3894 · Simon-Pierre Boucher · 8 days ago

wp18_uqo · 7301143 · Simon-Pierre Boucher · 20 days ago

…t est désormais la seule source de vérité du projet. Ancienne URL : https://www.llmindex.io LLM Index The discriminative, contamination resistant, fully transparent LLM ranking — updated live. www.llmindex.io · Methodolo…

PolyLLM One interface. Every model. Bring your own keys. — https://www.polyllm.io PolyLLM is a mobile first, multi model AI workspace — an "AI operating system" rather than a chat box: connect your own OpenAI, Anthropic,…

LLM API — A private, production grade, OpenAI compatible local LLM API for Apple Silicon . Store a large library of models on SSD, load only the one that is requested into unified memory, unload it when something else is…

…discovers, measures, and 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 . Ever…

🔥 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…

…One local endpoint. Every AI provider. Spec exact. Turn your Mac into a private LLM gateway — 170 models from 12 providers behind a single OpenAI compatible API. · · · · · · · · · · · 📖 Table of Contents Why Zyquo Route…

…, Mistral/Mixtral, Gemma 1–4, Phi 3/4, DeepSeek V3 distills, gpt oss, GLM 4, SmolLM3, LFM2, OpenELM, StarCoder2, Granite, and more — with a compatibility check before you download anything. True token streaming with a li…

…État Écran Action Chat — Mur définitif, soigné, sans culpabilisation Jamais de LLM de remplacement Explication Bouton « Ouvrir Réglages » Téléchargement en cours Bouton « Réessayer » ⚠️ Limitations connues Limitation Dé…

…ated: 2026 08 11 modified: 2026 08 12 status: reviewed localvm research Running LLMs larger than memory on a consumer Mac Live research platform: www.localvm.dev — every hypothesis, result, figure, and failure, browsable…

🔥 Forge Studio The Instruments of LLM training — 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 — a…

…hot is not committed ( documents provenance and checksum). Layout Reproduce The LLM second annotation ( ) needs in ; its labels are stored in so the rest of the pipeline runs without API access. Total LLM cost of the pro…

…hedonic studies included at stage 1), open access retrieval (501 PDFs, 18.8 %), LLM assisted extraction of 297 papers (242 eligible, 2,022 model columns, 18,831 coefficient rows; 20 paper independent double extraction: 1…

…entrants by transfer quintile; CEV by age after the surprise market clearing, Bellman residuals, grid/sample sensitivity (Appendix B) excess demand and ownership along the price (uniqueness scan) ownership, prices and pe…

…r documents the universe, the distributed acquisition/parsing architecture, the LLM extraction contract (two runs under one prompt lineage), the resolution rule and its failure modes, descriptive patterns, and a validati…

…red) Code & data reproducible from run from the repository root; raw crawls and LLM caches not committed Pre revision reference (v2.0), git tag 🎯 What this paper does Hedonic models are bounded by the characteristics an…

…scribes the architecture of VQuant, a platform that couples a reasoning capable LLM with a deterministic execution substrate, under the principle the model plans and synthesises, auditable code computes . It is written a…

…tes les photos, digest structuré de la description (text mining regex FR, aucun LLM), badge marché, historique de prix ( ), fiche PDF avec QR code. Couches de données de quartier — recensement 2021, registre des loyers (…

📝 JoF 250: Learning Scientific Writing Conventions from Pre LLM Financial Research UQO Working Paper No. 45 — A measured convention writing engine for Claude Code, built from 276 Journal of Finance articles (2017–2020),…

…ongside the Zyquo suite : six native macOS applications focused on AI and local LLMs. ✨ Features ⚡ Next.js 16 App Router — server components everywhere, static prerendering on every page 🎨 Tailwind CSS v4 + shadcn/ui st…

…dding compute, correlated opinions or persuasive prose. Twelve role specialised LLM agents (appraisal method, comparables, hedonic, market economist, building condition, geospatial risk, underwriting, buyer, seller, rent…