Local models are actually good now - playing with Qwen3.8-27B
A 4-bit Qwen3.8-27B built a cellular automata workbench locally on my M4 Pro, while 6-bit finished and 8-bit hit OOM.
Home / topic collection
MLX
Writing about MLX on billiem.
Writing
Latest first.
Fine-tuning a local LLM on Discord messages: where my clone failed
A local MLX LoRA experiment used my Discord messages to imitate my replies. Missing conversation turns limited what fine-tuning and retrieval could fix.