Sourced local AI setups for your Mac. Pick your chip and RAM, get the exact model, server and agent config that works.https://unifiedmem.dev/https://unifiedmem.dev/guides/claude-code-opencode-local-server/https://unifiedmem.dev/guides/claude-code-opencode-local-server/Point Claude Code and OpenCode at oMLX, Ollama or any OpenAI-compatible local server running Qwen3.6.Tue, 13 Oct 2026 00:00:00 GMThttps://unifiedmem.dev/guides/lora-fine-tuning-mlx/https://unifiedmem.dev/guides/lora-fine-tuning-mlx/QLoRA fine-tune a model on Apple Silicon with mlx-lm: data format, training, fusing and serving, with RAM guidance.Tue, 13 Oct 2026 00:00:00 GMThttps://unifiedmem.dev/guides/omlx-setup-and-tuning/https://unifiedmem.dev/guides/omlx-setup-and-tuning/Install oMLX, serve a Qwen3.6 model over OpenAI and Anthropic APIs, and tune the KV cache for long agent sessions.Tue, 13 Oct 2026 00:00:00 GMThttps://unifiedmem.dev/guides/qwen36-quant-by-ram/https://unifiedmem.dev/guides/qwen36-quant-by-ram/Which Qwen3.6 model and quantization fits your Mac's unified memory, with a simple sizing rule and per-tier picks.Tue, 13 Oct 2026 00:00:00 GMThttps://unifiedmem.dev/guides/why-is-my-mac-slow/https://unifiedmem.dev/guides/why-is-my-mac-slow/Work out whether slowness comes from prefill, swap, bad defaults, the runtime or the agent harness, and fix it.Tue, 13 Oct 2026 00:00:00 GMThttps://unifiedmem.dev/blog/launch/https://unifiedmem.dev/blog/launch/Why we built a Mac-only, sourced, config-first resource for running local LLMs and coding agents.Tue, 13 Oct 2026 00:00:00 GMT