← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

BigMoeOnEdge

github.com

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

MobileOpen source

Visit github.comexternal siteGitHub735 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. Edge0

    Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

    GitHub9,177 starsgithub.comOpen sourcelatest reaction

  2. Capy-flash

    a 125B MoE model on two 16 GB consumer GPUs

    Hacker News8 ptsGitHub140 starsgithub.comOpen source2 reactionslatest reaction

  3. llama-modchip

    🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.

    Hacker News428 ptsGitHub635 starsgithub.comOpen source2 reactionslatest reaction

  4. vLLM-Moet

    Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0

    GitHub571 starsgithub.comOpen sourcelatest reaction

  5. I run 30B 22tok/s, 109tok/s not novel,6GB/16GB RAM overcoming llama.cpp

    Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGUF on your exact hardware, self-calibrates, emits the exact llama.cpp command — or 'quantprobe auto' does it all. Falsification-tested laws; misses published at full size. pip install quantprobe

    Hacker News5 ptsGitHub93 starsgithub.comOpen source2 reactionslatest reaction