Tag: quantization

All the articles with the tag "quantization".

• Run Qwen3.8 27B locally: real numbers from my Mac Studio

  27 Aug, 2026

  Qwen3.8 27B benchmarked on a Mac Studio M3 Ultra: Ollama and llama.cpp numbers, the 1-bit quant tested, RAM math, and the hardware that actually fits.

  • qwen
  • local-llm
  • ollama