Perplexity has open sourced Lily, a Rust and Metal inference engine for Qwen3.6-35B-A3B on Apple Silicon, achieving a 77.4% prefill speedup via fused grouped GEMM and an 89% gain from GPU-only routing…
Salvatore Sanfilippo, the creator of Redis known as antirez, demonstrated DeepSeek V4 Flash with vision running locally on a Mac M5 Max on September 1, 2026, and announced that Metal, CUDA, and ROCm b…
Independent developer Carlos Galarza released slotstream, a Swift binary that streams Mixture-of-Experts model tensors from NVMe SSD into Apple Silicon Metal memory, enabling local inference of Alibab…
LerSent001 released Liquid Orb Editor, a real-time liquid glass orb editor built with React, WebGPU/WGSL, and Toolcraft UI, offering 12 editable dynamic sphere presets, parameter controls for color, s…
Apple's Metal GPU glossary 'metalworking' targets developers familiar with CUDA but new to Apple Silicon, mapping every concept from GPU cores to MLX's architecture with CUDA equivalents and real kern…
WebGPU is a paradigm shift for web development, enabling massively parallel computing directly in the browser. It replaces the rigid WebGL pipeline with explicit compute shaders, allowing developers t…
A developer has released a CUDA-optimized fork of antirez's h3.c for NVIDIA DGX Spark, achieving a ~15.5x speedup, while also providing a native Apple Silicon implementation for MiniMax-H3 inference w…
Local-first workspace software can eliminate the need for cloud indexing by leveraging on-device AI and search capabilities, according to a guide from Neutron Tech. Modern hardware such as Apple Silic…
VPIPE, a new macOS app from developer tgo-app-dev, runs MiniMax H3, a 33B multimodal model generating video and audio, on Apple Silicon Macs with as little as 16 GB RAM, achieving a 5-second 0.5 MP 24…
A developer has detailed a methodology for building a fully offline, portable AI assistant that runs from a USB drive on an Apple M4 Mac mini with 16 GB RAM. The approach leverages llamafile and GGUF …
A new open-source Rust project, tts-rs, delivers local text-to-speech on Apple silicon with three voice-cloning engines ported from PyTorch, achieving real-time factors as low as 0.252 for the Qwen3TT…
A team at Cua has developed a process-scoped Metal capability shim that unlocks 11-16x faster LLM inference in macOS virtual machines on Apple Silicon, bringing VM performance to 94-99% of bare-metal …
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…
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…
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…
Swiftlet, a Swift + Metal runtime for Qwen3-Next and Qwen3.5/3.6 MoE hybrid models, runs an 80B Qwen in 4.3 GB of RAM on a Mac and a 35B on an iPhone 17 in about 2.5 GB of RAM at about 1 token per sec…
Symbio, a local AI assistant that learns from user corrections and fine-tunes itself without cloud or subscriptions, was released on GitHub by developer HuyEdits. The system runs on Apple Silicon usin…
A developer has released TurboFieldfare, an open-source Swift and Metal engine that runs Google's Gemma 4 26B-A4B instruction-tuned model in about 2 GB of RAM on any Apple Silicon Mac, including 8 GB …
A developer released Minute, a macOS app that transcribes and summarizes meetings offline using local Whisper and llama.cpp models, with no cloud dependency or telemetry. Built with Tauri, Rust, React…
Fermion Research has published Neutrino-1 8B, an 8.19-billion-parameter language model packaged in a 3.88 GB file that fits on an 8 GB GPU or 16 GB laptop, using a proprietary ternary-family format th…