Pythonic binding to the Apple Neural Engine

A 3D mesh viewer for the Linux terminal written in C!

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Gemma 4 26B-A4B SSD-streaming inference for Windows/Linux — Rust port of TurboFieldfare

TurboFieldfare 로컬 추론 서버를 위한 인증, TLS, 요청 제한 및 감사 로그 운영 게이트웨이

Minimal tensor computation framework in pure Go with SIMD assembly, inspired by tinygrad

Run Qwen3.6 35B on Apple M1-M5 with low RAM usage using SSD/NVM streaming.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

AirLLM 70B inference with single 4GB GPU

Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Smal…

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

Ultra-minimalist macOS recording + transcription.

Run large Mixture-of-Experts language models well on the memory you have.

Memory-aware GGUF inference runtime with OpenAI-compatible serving

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

A high-performance multi-language bindings generator for Rust, up to 1,000x faster than UniFFI. Ship Rust libraries that feels native to Python, Swift, Kotlin, and more

Runs 405B LLMs on 8GB VRAM

A cross-platform, safe, pure-Rust graphics API.

MentraOS is the leading smart glasses OS. See live captions, stream your view, talk to AI, and capture photos hands-free on compatible glasses.

A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.

Language model tokenization at GB/s

A brief computer graphics / rendering course

Kali Linux on the Youyeetoo X1S: NVMe rebuild, thermal testing, local AI benchmarks, and a loopback security workflow

Seven Minutes Is All I Can Spare To Play With You.