Reading up on LM Studio

A developer details setting up a local coding agent on macOS using llama.cpp, Gemma 4, and Pi for real-time terminal-based AI assistance.

Local agentic coding models have reached surprising quality and usability over the past six months, now offering ~75% of frontier-model accuracy for many development tasks on a 64GB M2 Mac.

Google's Gemma 4 12B model uses Multi-Token Prediction and a streamlined multimodal encoder to run efficiently on laptops with 16GB RAM, matching larger models.

A guide for running Gemma 4 models locally on a Mac Mini via Ollama, with commenters reporting that the 26B variant is too slow and memory-intensive for daily use, while smaller quantizations suffice for light tool-calling tasks.

Unsloth launches Unsloth Studio, an open-source, no-code web UI for locally running, training, and exporting 500+ open models with 2x faster training and 70% less VRAM.

The site canirun.ai estimates which local AI models a given machine can run based on hardware specs, but commenters found its RAM detection and speed predictions inaccurate for modern hardware.

LLMFit is a terminal tool that scans system hardware and scores LLM models on fit, speed, and quality to recommend which can run locally.

Apple announces MacBook Pro with M5 Pro and M5 Max, claiming up to 4x faster LLM prompt processing and up to 8x AI image generation over prior generations.

LM Studio 0.4 introduces a headless server daemon (llmster), parallel requests with continuous batching, a refreshed UI, and a new stateful REST API.

Local coding models are not yet worth the hardware cost for most users, as proprietary cloud models offer better quality and lower upfront investment.