← Trending

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

vLLM-Moet

github.com

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

Open source

Visit github.comexternal siteGitHub571 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. DeepSeek-V4

    The open-source era of 1M context intelligence

    Hacker News7 ptsProduct Hunt378 voteshuggingface.co2 reactionslatest reaction

  2. 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

  3. Capy-flash

    a 125B MoE model on two 16 GB consumer GPUs

    Hacker News8 ptsGitHub140 starsgithub.comOpen source2 reactionslatest reaction

  4. DeepSeek-V4-Flash-0731

    Frontier agent intelligence at Flash prices

    Hacker News16 ptsProduct Hunt320 voteshuggingface.co2 reactionslatest reaction

  5. BigMoeOnEdge

    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.

    GitHub735 starsgithub.comMobileOpen sourcelatest reaction