SNSandeep Nayak

Sandeep Nayak

Notes from building data pipelines and running LLMs on my own hardware, with the numbers I measured.

Writing

  1. · 11 min read

    llama.cpp vs BaseRT vs colibri: local LLM inference on an M1 Max, measured on a real workload

    Four inference engines, one MoE model, one MacBook: websites per hour on a real long-prompt JSON extraction job.

    Read post →