Results for “mlx”

The local MLX foundry for your Mac — run, fine-tune, quantize, and ship models. Nothing leaves your machine.

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

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

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

zyquo-mlx · main

zyquo-local · main

tools-spboucher-ai · main

tools-spboucher-ai · main

tools-spboucher-ai · main

wp30_uqo · main

wpai0001_uqo · main

llm-api · main

modelmap · main

wpai0001_uqo · main

llm-api · main

metrika · main

wp33_uqo · main

zyquo-mlx · main

spboucher.ai · main

zyquo-mlx · main

zyquo-mlx · main

zyquo-mlx · main

wpai0001_uqo · main

zyquo-mlx · main

wpai0001_uqo · 1d0896f · Simon-Pierre Boucher · 6 h ago

Zyquo MLX The local MLX foundry for your Mac — run, fine tune, quantize, and ship models. Nothing leaves your machine. Where Zyquo Local is the chat client, Zyquo MLX is the foundry: the complete workbench for the on dev…

…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 · Notarized by Apple · Stap…

…ll report: TR 2026 01) Finding Evidence Activation capture is nearly free under MLX — 1.004× plain prefill on a real 4 bit checkpoint (first Python capture from an actually quantized local model) expH, 3 registered runs…

…d protocol, the experiment harness (toy transformers with exact hook semantics; MLX/Transformers backends planned), the registry of runs and the paper. Result (Tier 0, preregistered confirmatory run, 2026 11 09): a donor…

…tion 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 evaluator only fact l…

…s Item Value Version 1.0 (October 2026) Phases executed 0–10, 13–15 (see ); 11 (MLX port) not executed; 12 limited to meta instantiation Decisive experiments 5 adapter seeds × {sparse editor, global recurrence, dense wri…

…nified interface Repo · Release · DMG 💻 Zyquo Local 100% local LLMs with Apple MLX — private, offline, no API keys Repo · Release · DMG 🤖 Zyquo Agent Autonomous AI agent for the Mac — tool calling, automation, multi st…

…Paper No. 33 — A Measured Systems Study on a Heterogeneous Mac Cluster TL;DR An MLX native MoE inference runtime with bounded per layer expert residency (slot tables), a NVMe tier, LRU/LFU eviction, causal prefetch predi…

…us any OpenAI compatible endpoint such as Ollama, LM Studio, vLLM, llama.cpp or MLX), discover the models your keys can reach, configure each one with only the parameters it supports, chat with real token by token stream…

…st. Switches are serialized; requests queue while a model loads. Two runtimes : MLX / MLX LM (preferred, safetensors) and llama.cpp (GGUF, Metal). Each model runs in its own worker process on — killing the process is how…

…verification (U HLM/UGSD, vs cloud), window amortized verification (SpecExec), MLX layer streaming (mlx flash). Four narrow claims survived: (N1) margin gating of the same model's higher precision weight streaming I/O o…

…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 complete, worki…

…he GPU is invisible. A planner dispatches every command to CPU (LAPACK) or GPU (MLX) automatically. Large bootstrap runs execute as batched Metal solves; you never choose a backend. Reproducibility is a feature, not an a…

…contact@spboucher.ai Part of the Zyquo family — Cloud · Local · Agent · Atlas · MLX · Router © 2026 Simon Pierre Boucher. All rights reserved.…