← 최신 프로덕트

OpenGraviton

Run 500B+ parameter models on a consumer Mac Mini. The system combines several techniques to drastically reduce memory and compute requirements: • 1.58-bit ternary quantization ({-1, 0, +1}) for ~10x compression • dynamic sparsity with Top-K pruning and MoE routing • mmap-based layer streaming to load weights directly from NVMe SSDs • speculative de.

opengraviton.github.io 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Run 500B+ Parameter LLMs Locally on a Mac Mini

    github.com

    By combining 1.58-bit ternary quantization, dynamic sparsity with Top-K pruning and MoE routing, and mmap-based layer streaming, OpenGraviton can run models far larger than your system RAM—even on a Mac Mini.

    Hacker News17점

  2. Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload

    github.com

    OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

    Hacker News22점

  3. Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE

    github.com

    Metal-first MoE inference for Apple Silicon with bounded SSD expert streaming and local OpenAI Chat, Responses, and Anthropic Messages endpoints.

    Hacker News24점

  4. 80% faster

    github.com

    50% less memory, 0% loss of accuracy Llama finetuning

    Hacker News385점

  5. Minimal LLM Post-Training Experiments on an 8GB GPU (SFT

    github.com

    DPO, GRPO)

    Hacker News21점