Apertura, a from-scratch Objective-C++/MLX rebuild of Google's Gemma-4 for Apple Silicon, runs the entire Gemma-4 text family natively on a Mac with bit-exact conformance to the PyTorch reference, ach…
The memory ceiling on local GPUs is the most reliable predictor of cloud inference cost trends, according to an analysis of 2026 hardware and pricing data. The article calculates that a 70B model requ…
Intersignal's Braid v1.5.2 transferred signed semantic context between two local AI systems using different embedding models, a test of its protocol for moving machine state without cloud platforms. T…
LabLLM, a free native macOS app built with SwiftUI and Apple MLX, lets users train small GPT-style Transformer and LLM models from scratch on Apple Silicon (M1 or newer, macOS 14+). The beta supports …
A new C++ implementation of NVIDIA's Sana 0.6B text-to-image model, named Sana.cpp, runs approximately 4.8 times faster than the PyTorch pipeline on Apple Silicon CPU. The project, developed by GitHub…
Apple's Core AI framework, introduced at WWDC 2026, enables fully on-device AI agents with local language models up to 70 billion parameters, eliminating latency and privacy concerns of cloud-based AI…
A developer replaced GitHub Copilot with a fully offline coding assistant running on a 16GB M4 Mac mini using Ollama and Qwen models. They found that a 7B parameter model is the sweet spot for chat an…
A developer has released a clone-and-run launcher that runs LTX-2.5 text-to-video generation locally on Apple Silicon in a single command, with audio support and no need for ComfyUI or CUDA. The launc…
PhotonicOps, an offline, air-gapped telemetry ingestion and agentic hardware-triage engine for silicon photonic biosensors, chose gRPC over a Unix socket instead of HTTP for its internal Go-to-Python …
NeutronTech launched Hubyn (HBM), a private messaging and workspace app for iOS and macOS that operates without a phone number, using a private PIN for connections and on-device AI on Apple Silicon. T…
Antirez released h3.c, a native MiniMax-H3 inference engine for Apple Silicon Macs, with prompt-to-video/audio, first/last-frame conditioning, and ordered Ref2VA references working end to end. The pro…
Meta Superintelligence Labs released Muse Glimmer, a 30B multimodal open model for local agent workloads, now available on Ollama with initial support for Apple Silicon via the MLX engine. The model, …
Mac-stats, a free MIT-licensed menu-bar system monitor for Apple Silicon Macs, now includes an optional local AI agent powered by Ollama that is off by default, alongside CPU, SSD, and temperature mon…
Meta released Muse Glimmer 30B, its first open-weights model in the Muse family, under the Apache 2.0 license, featuring a 1.8B vision encoder and a 128K+ context window for coding, agentic workflows,…
FastVideo released FastMetal-QAD, a family of three open-source video generation models (1.3B, 5B, and 14B) that run natively on Apple Silicon via a new MLX runtime, with the 5B model generating a fiv…
Meta Superintelligence Labs released Muse Glimmer, a 30-billion-parameter multimodal open model under Apache 2.0, designed for local agent workloads on consumer hardware. The model scores 76 on SWE-Be…
A developer has published a practical guide for setting up a local AI troubleshooting and support environment on macOS and Windows using Open WebUI, Ollama, and Hugging Face. The recommended architect…
Lyogavin has released AirLLM, an open-source Python library that enables running 70B parameter large language models on GPUs with as little as 4GB of VRAM. By streaming model layers sequentially from …
PipeNetwork released minimax-h3-mlx, a community MLX implementation of MiniMax-H3 for Apple Silicon, translating the 33-billion-parameter video-and-audio diffusion pipeline into native MLX. The reposi…
Eigen Labs' lead research engineer Gajesh Naik said on August 1st that a public network of developers and AI agents made Poolside's Laguna XS 2.1 inference 138.7% faster on Apple Silicon, four days af…