#swift #ai #aichat #chatbot #chatgpt #deepseek #deepseek_r1 #gemma #gemma3 #gguf #llama #llama3 #llm #macos #qwen #qwen2 #qwq #qwq_32b #rag #swift #swiftui

Sidekick is a local-first AI application for Macs that helps you find information from your files, folders, and websites without needing the internet. It's private, so your data stays secure on your device. You can ask questions like "Did the Aztecs use captured Spanish weapons?" and get answers with references. Sidekick also supports image generation, LaTeX rendering, and more. This makes it useful for research and work because it keeps your data safe and provides quick access to relevant information.

https://github.com/johnbean393/Sidekick

#python #ai #apple_silicon #benchmarks #cli #command_line_tool #gguf #gpu #huggingface #inference #llm #local_llm #ollama #python #vram

whichllm helps you find the best local AI model that fits your computer, not just the biggest one that fits. It checks your GPU, CPU, and RAM, ranks models using real benchmark data, and can also simulate other hardware, plan upgrades, and start a chat with a model in one command. This saves you time and helps you pick a model that should run well and work better for your needs.

https://github.com/Andyyyy64/whichllm

#cplusplus #asr #ggml #gguf #speech_to_text

transcribe.cpp is a fast, free C/C++ library that turns speech into text using 16 model families (like Whisper and Parakeet) on your own GPU or CPU, with official supports for Python, JavaScript, Rust, and Swift. You benefit by getting accurate, verified transcriptions without paying cloud API fees, running entirely on your device for privacy, and supporting streaming, batch, and specialized tasks like medical dictation or speaker diarization.

https://github.com/handy-computer/transcribe.cpp

#rust #gguf #llm #localai #mlx #skill #unsloth

llmfit is a free terminal tool that automatically checks your computer’s RAM, CPU, and GPU to tell you exactly which large language models will run well on your machine, ranking them by fit, speed, quality, and context. It supports both an interactive visual interface and a command-line mode, works with multi-GPU setups, and suggests the best quantization levels so you never waste time or storage downloading models that won’t work. This saves you from guesswork, trial-and-error testing, and wasted bandwidth, giving you immediate, reliable recommendations for the best local AI models for your specific hardware.

https://github.com/AlexsJones/llmfit