1
Run Qwen3.8 27B locally: real numbers from my Mac Studio
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.
Tech blog covering mini PCs, homelab, self-hosting, gaming servers, and DevOps experiments.
Visit terminalbytes.com → RSS feedOn Hacker News Jun 2025 – Aug 2026
Hardware & Electronics 2Tools & Productivity 1AI & Machine Learning 1
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.