HN Explorer

fatihturker

↗ HN profile [ 41.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 1
  2. Show HN: Efficient LLM Architectures for 32GB RAM (Ternary and Sparse Inference) (github.com)

    Hi HN, I’ve been exploring how far large language models can be pushed on machines with limited memory. I built an experimental runtime and architecture approach focused on making extremely large models more feasible on…

    2 points 1
  3. Show HN: Run 500B+ Parameter LLMs Locally on a Mac Mini (github.com)

    Hi HN, I built OpenGraviton, an open-source AI inference engine that pushes the limits of running extremely large LLMs on consumer hardware. By combining 1.58-bit ternary quantization, dynamic sparsity with Top-K…

    17 points 12
  4. Could ternary weights make 500B models runnable on consumer hardware? (opengraviton.github.io)
    7 points 5
  5. Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini (opengraviton.github.io)

    Hi HN, I built OpenGraviton, an open-source AI inference engine designed to push the limits of running extremely large models on consumer hardware. The system combines several techniques to drastically reduce memory and…

    13 points 4